© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73505
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.71
     noses
    -0.55
    oa̍t
    -0.55
    LookAnd
    -0.54
    TypedDataSet
    -0.54
    gole
    -0.53
     Solon
    -0.52
    ChildScrollView
    -0.52
     Perse
    -0.52
     insertions
    -0.51
    POSITIVE LOGITS
    withIdentifier
    0.52
     mềm
    0.52
     travaux
    0.46
    phosa
    0.44
    Interess
    0.43
    انظر
    0.43
     lembut
    0.42
     poils
    0.42
    المراجع
    0.42
     stället
    0.42
    Activations Density 0.000%

    No Known Activations