© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92188
    Prev
    Next
    INDEX
    Explanations

    {

    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
    UrlResolution
    -0.73
    cstring
    -0.67
     AssemblyCulture
    -0.66
    xido
    -0.64
    rinol
    -0.63
     Reverso
    -0.62
    qrstuvwxyz
    -0.62
    شهاد
    -0.60
    بوابة
    -0.60
    extAlignment
    -0.60
    POSITIVE LOGITS
     intptr
    0.68
    abestanden
    0.63
    Personendaten
    0.54
    KURZBESCHREIBUNG
    0.52
    UIControlState
    0.48
     inalámb
    0.48
     ū
    0.47
     Kir
    0.46
    PathVariable
    0.45
    regon
    0.44
    Activations Density 2.063%

    No Known Activations