Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13185
    Prev
    Next
    INDEX
    Explanations

    news articles related to political events and international conflicts.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1535
    +0.23
    0.8%
    382
    +0.22
    0.7%
    2034
    +0.22
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.10
    1535
    +0.22
    0.07
    752
    +0.22
    0.05
    Negative Logits
     Endlich
    -1.10
     geforce
    -1.03
     embodi
    -1.01
     viciss
    -1.00
    Cześć
    -0.99
     Darum
    -0.97
     theolog
    -0.96
     mondeo
    -0.95
     logitech
    -0.95
     Zwar
    -0.93
    POSITIVE LOGITS
     However
    0.79
     The
    0.78
     But
    0.76
     It
    0.76
    ↵↵
    0.75
     They
    0.72
     This
    0.71
     Since
    0.70
     Its
    0.70
    <bos>
    0.69
    Activations Density 0.271%

    No Known Activations