© 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
    2. Gemma-2-2B
    3. 22-RES-MATRYOSHKA-DC
    4. 1629
    Prev
    Next
    INDEX
    Explanations

    image captions and references to figures

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     section
    -0.67
     Section
    -0.63
    Section
    -0.58
    section
    -0.58
     sections
    -0.55
     Sections
    -0.55
     Abschnitt
    -0.51
     list
    -0.48
     listed
    -0.46
     references
    -0.46
    POSITIVE LOGITS
     figure
    1.47
    figure
    1.47
     FIGURE
    1.47
    FIGURE
    1.41
     Figure
    1.40
    Figure
    1.39
    FIG
    1.30
    fig
    1.29
     FIG
    1.29
     Fig
    1.28
    Activations Density 1.180%

    No Known Activations