© 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. 1964
    Prev
    Next
    INDEX
    Explanations

    possessive nouns

    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
    ConstraintMaker
    -0.62
    fty
    -0.55
     OMITBAD
    -0.51
     Independencia
    -0.50
    burgo
    -0.50
     avanzar
    -0.50
    🧼
    -0.50
     competir
    -0.49
    GenerationType
    -0.48
     rentrer
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.76
     createStore
    0.66
     >=",
    0.66
    ContentAlignment
    0.65
    EDEFAULT
    0.63
     дописавши
    0.62
     Italijanski
    0.62
    oples
    0.61
     disambiguazione
    0.61
    homonymie
    0.61
    Activations Density 0.225%

    No Known Activations