© 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. 5-CLT-HP
    7. 95222
    Prev
    Next
    INDEX
    Explanations

    name

    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
    MigrationBuilder
    -0.50
    <eos>
    -0.48
    ⤹
    -0.45
     efficiencies
    -0.44
     inefficient
    -0.44
    tamol
    -0.42
    adillas
    -0.42
     مرئيه
    -0.41
    Portail
    -0.41
     snee
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.60
     Paglinawan
    0.54
    djangoproject
    0.54
     band
    0.54
    pushFollow
    0.53
    npmjs
    0.53
    MessageState
    0.52
     Atty
    0.52
    enumi
    0.52
    yarnpkg
    0.51
    Activations Density 0.006%

    No Known Activations