© 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. 4-CLT-HP
    7. 3254
    Prev
    Next
    INDEX
    Explanations

    Describing events/actions

    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
    findpost
    -0.63
    raires
    -0.58
    Personendaten
    -0.56
    juvant
    -0.55
    tanleria
    -0.54
    encodeWith
    -0.54
    mika
    -0.53
    ⓧ
    -0.53
    нциклопедия
    -0.52
     Supremo
    -0.52
    POSITIVE LOGITS
     us
    1.46
     me
    1.45
     himself
    0.71
     some
    0.69
     conmigo
    0.66
    لينا
    0.66
     herself
    0.66
     meille
    0.63
     his
    0.60
     нами
    0.59
    Activations Density 0.004%

    No Known Activations