© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1144
    Prev
    Next
    INDEX
    Explanations

    polar regions and seas

    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
     itſelf
    -1.11
     Theſe
    -1.09
     AssemblyCulture
    -1.07
     ་་
    -1.05
    MigrationBuilder
    -1.05
     doubtnut
    -1.04
     ―――――
    -1.03
     Efq
    -1.02
    KURZBESCHREIBUNG
    -0.98
     utafitiHapana
    -0.97
    POSITIVE LOGITS
     
    0.76
     I
    0.74
    .
    0.71
     or
    0.66
     in
    0.65
     (
    0.65
    ,
    0.64
     and
    0.63
     of
    0.63
    s
    0.62
    Activations Density 0.046%

    No Known Activations