© 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. 5-CLT-HP
    7. 91341
    Prev
    Next
    INDEX
    Explanations

    cult

    np_max-act · 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
     ModelExpression
    -0.65
     AssemblyTitle
    -0.59
     egyéb
    -0.54
     also
    -0.53
     previously
    -0.52
    stdc
    -0.52
    Референце
    -0.52
     GenerationType
    -0.52
    Referències
    -0.50
    TemporalType
    -0.50
    POSITIVE LOGITS
    Datuak
    0.73
    WebControls
    0.66
    VersionUID
    0.65
    цездатний
    0.63
    usammen
    0.61
    AndEndTag
    0.59
    argout
    0.59
    Brainz
    0.57
    abatic
    0.57
    ticons
    0.56
    Activations Density 0.008%

    No Known Activations