© 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. 12343
    Prev
    Next
    INDEX
    Explanations

    technical terminologies and numeric data associated with measurements or results in scientific studies

    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
    RenderAtEndOf
    -0.95
    GEBURTSDATUM
    -0.72
    +:+
    -0.68
    transQ
    -0.63
    WebVitals
    -0.58
    StructEnd
    -0.58
    новниш
    -0.57
    сылкі
    -0.57
    ConstraintMaker
    -0.57
    UrlResolution
    -0.56
    POSITIVE LOGITS
     виправивши
    0.92
    ByExample
    0.54
    ض
    0.49
    Autoritní
    0.47
     урна
    0.47
     incomplète
    0.46
    FXML
    0.46
    Bibliografie
    0.45
     informée
    0.45
    DockStyle
    0.45
    Activations Density 0.000%

    No Known Activations