© 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. 38795
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    حياتها
    -0.68
    »?
    -0.67
    حياته
    -0.65
     насељу
    -0.64
    γραφία
    -0.63
    OGND
    -0.62
    ”?
    -0.59
     Signalez
    -0.57
    UrlResolution
    -0.57
    pierw
    -0.56
    POSITIVE LOGITS
     secretly
    0.60
     really
    0.59
     finally
    0.58
     gently
    0.56
     substantially
    0.56
     briefly
    0.55
     clearly
    0.55
    MigrationBuilder
    0.54
     veramente
    0.54
     easily
    0.54
    Activations Density 0.066%

    No Known Activations