© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7760
    Prev
    Next
    INDEX
    Explanations

    phrases related to whistleblowers and incidents of retaliation

    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
    889
    +0.10
    0.3%
    168
    +0.09
    0.3%
    1314
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.10
    0.02
    1314
    +0.09
    0.02
    944
    +0.09
    0.02
    Negative Logits
     كومونز
    -0.54
     Normdatei
    -0.52
     frans
    -0.50
    Cuánt
    -0.50
    脚注の使い方
    -0.49
     CreateTagHelper
    -0.49
    RegistryLite
    -0.48
    Zend
    -0.48
     Ferne
    -0.47
    OGND
    -0.47
    POSITIVE LOGITS
     whistle
    1.15
     whist
    1.12
     Whistle
    1.10
     whistles
    1.01
     Whist
    0.91
     whistling
    0.91
     whistled
    0.89
    histle
    0.81
    blower
    0.74
     Lmao
    0.73
    Activations Density 0.108%

    No Known Activations