© 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. 22-RES-MATRYOSHKA-DC
    7. 1986
    Prev
    Next
    INDEX
    Explanations

    contractions where 't' is the last letter in the word

    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
     be
    -1.63
    be
    -1.26
    Be
    -1.16
     soient
    -1.12
     Be
    -1.11
    BE
    -0.90
     BE
    -0.87
     siano
    -0.84
     être
    -0.82
     aient
    -0.79
    POSITIVE LOGITS
    PreferredItem
    1.06
    ThroughAttribute
    1.00
    LookAnd
    0.96
     seem
    0.90
    ":[{
    0.90
    setVerticalGroup
    0.90
    aarrggbb
    0.90
     ModelExpression
    0.89
    MigrationBuilder
    0.88
     deserve
    0.88
    Activations Density 0.278%

    No Known Activations