© 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. 1-CLT-HP
    7. 9222
    Prev
    Next
    INDEX
    Explanations

    trees

    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
    eleste
    -0.62
    Abp
    -0.60
     OnInit
    -0.59
    WebElementEntity
    -0.57
    grano
    -0.57
     Crack
    -0.51
     Usher
    -0.51
    ltä
    -0.51
    akaan
    -0.51
    pars
    -0.51
    POSITIVE LOGITS
     صوتيه
    0.59
    IndentedString
    0.59
    FXMLLoader
    0.59
    myModal
    0.54
     defStyle
    0.52
    Risultati
    0.48
    chelsea
    0.46
    UseVisualStyle
    0.46
    rrggbb
    0.45
     snippetHide
    0.44
    Activations Density 0.076%

    No Known Activations