© 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. 0-RES-MATRYOSHKA-DC
    7. 11926
    Prev
    Next
    INDEX
    Explanations

    references to specific individual entities or persons

    oai_token-act-pair · gpt-4.1-nano
    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
    GenerationType
    -0.58
    談社
    -0.55
     obstante
    -0.54
    饱
    -0.53
    angsaan
    -0.51
    mediaType
    -0.51
    ARROLL
    -0.50
    oplayer
    -0.50
    benefit
    -0.49
     JMenuItem
    -0.48
    POSITIVE LOGITS
    iden
    3.45
    IDEN
    2.30
    idens
    1.27
    ident
    0.88
    idend
    0.85
    Iden
    0.71
    idenza
    0.69
    multer
    0.65
    pushFollow
    0.64
    новниш
    0.63
    Activations Density 0.000%

    No Known Activations