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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17610
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception or perception by others

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.78
    fromnode
    -0.66
    mappedBy
    -0.63
    原始内容存档于
    -0.62
    البته
    -0.59
    PropertyGroup
    -0.58
    atigable
    -0.58
     pribadi
    -0.57
     ourselves
    -0.57
    enumii
    -0.56
    POSITIVE LOGITS
    ettbewer
    0.60
    [:]
    0.54
    ẾT
    0.51
    QWidget
    0.50
     spot
    0.50
    addCriterion
    0.49
    soy
    0.48
    romic
    0.48
     everything
    0.48
    netbeans
    0.48
    Activations Density 0.084%

    No Known Activations