© 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. 96086
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    UserScript
    -0.91
     ostavi
    -0.82
    Personendaten
    -0.82
     estekak
    -0.81
    úgó
    -0.81
     Diſ
    -0.78
    AttributeSet
    -0.75
     purpoſe
    -0.73
     שוליים
    -0.72
    ſelf
    -0.71
    POSITIVE LOGITS
     “
    0.48
     a
    0.48
     his
    0.45
     an
    0.42
     "
    0.42
     her
    0.41
    zu
    0.41
     the
    0.41
    TypeDef
    0.41
     meng
    0.40
    Activations Density 0.002%

    No Known Activations