© 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. 3-RES-MATRYOSHKA-DC
    7. 2991
    Prev
    Next
    INDEX
    Explanations

    instances of the word "public" and words close to it

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.69
    protected
    -0.65
    CreateModel
    -0.63
    principalTable
    -0.63
    issau
    -0.59
    static
    -0.58
     îna
    -0.57
    Expedia
    -0.57
     espirituales
    -0.57
    contentLoaded
    -0.56
    POSITIVE LOGITS
     public
    0.95
     Public
    0.92
     öffentlichen
    0.84
    Public
    0.82
     PUBLIC
    0.77
     publique
    0.75
     pública
    0.75
    AnimationsModule
    0.73
     público
    0.70
     öffentliche
    0.70
    Activations Density 0.023%

    No Known Activations