© 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. 2330
    Prev
    Next
    INDEX
    Explanations

    terms related to the use of software or information

    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
    gebnisse
    -0.62
     Eggers
    -0.60
     Cached
    -0.60
    laken
    -0.59
    berian
    -0.57
    Cached
    -0.57
    constructor
    -0.56
     Erik
    -0.56
     Schmitz
    -0.56
    jectives
    -0.56
    POSITIVE LOGITS
    Hochspringen
    0.88
    makeConstraints
    0.80
     ExecuteAsync
    0.80
     transfieras
    0.75
    Vidite
    0.75
     itſelf
    0.74
     Roskov
    0.74
    InjectAttribute
    0.72
    elemField
    0.72
     myſelf
    0.71
    Activations Density 0.087%

    No Known Activations