© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6640
    Prev
    Next
    INDEX
    Explanations

    companies rated as "neutral" in financial contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    966
    +0.14
    0.6%
    2004
    +0.13
    0.6%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.03
    1896
    +0.13
    0.02
    1351
    +0.11
    0.02
    Negative Logits
    <bos>
    -1.56
     Margot
    -0.57
    FlatAppearance
    -0.56
    QMetaType
    -0.56
    FormBorderStyle
    -0.55
    Ан
    -0.53
    Hvad
    -0.52
     OnDestroy
    -0.52
    которы
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    POSITIVE LOGITS
     Neutral
    1.23
     neutral
    1.20
     Bias
    1.19
    Neutral
    1.18
     bias
    1.17
    Bias
    1.16
    bias
    1.12
    neutral
    1.10
     biases
    1.01
     biased
    1.01
    Activations Density 0.309%

    No Known Activations