© 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. 20-CLT-HP
    7. 73160
    Prev
    Next
    INDEX
    Explanations

    ll

    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
     propOrder
    -0.93
    LookAnd
    -0.87
    WithIOException
    -0.80
    extAlignment
    -0.77
    HandlerContext
    -0.75
     Hopes
    -0.75
    исленность
    -0.75
     raiſ
    -0.71
    SpringBootTest
    -0.71
     iconFacebook
    -0.71
    POSITIVE LOGITS
    nu
    0.42
     puestos
    0.42
     im
    0.37
    auer
    0.36
    yy
    0.35
    (['/
    0.35
    BindView
    0.35
    戴
    0.35
    uo
    0.34
    igold
    0.34
    Activations Density 0.000%

    No Known Activations