© 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. 5-CLT-HP
    7. 93530
    Prev
    Next
    INDEX
    Explanations

    Israel

    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
    UnusedPrivate
    -0.57
    CrossRef
    -0.48
    ANTLR
    -0.48
    IonicModule
    -0.46
    addPreferredGap
    -0.45
     yw
    -0.45
    thenia
    -0.44
     Winkel
    -0.44
    脚注の使い方
    -0.44
     pari
    -0.44
    POSITIVE LOGITS
    ousands
    0.63
    TypedDataSet
    0.61
     transfieras
    0.60
     ProtoMessage
    0.59
     Infórmanos
    0.56
    PreferredItem
    0.54
    aarrggbb
    0.52
    CodedInputStream
    0.51
     pard
    0.51
     blasphemy
    0.51
    Activations Density 0.002%

    No Known Activations