© 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. 990
    Prev
    Next
    INDEX
    Explanations

    technology and science

    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
    lander
    -0.70
    <eos>
    -0.54
     prestige
    -0.50
    landers
    -0.48
    tri
    -0.47
     Le
    -0.46
     be
    -0.44
     food
    -0.43
     le
    -0.43
     contact
    -0.43
    POSITIVE LOGITS
     disambiguazione
    1.08
     Efq
    1.05
     OMITBAD
    1.05
     resourceCulture
    0.98
     ProtoMessage
    0.98
    MigrationBuilder
    0.91
     initComponents
    0.90
    verwijspagina
    0.90
    MessageOf
    0.90
     للاسماء
    0.89
    Activations Density 0.085%

    No Known Activations