© 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. 1-CLT-HP
    7. 528
    Prev
    Next
    INDEX
    Explanations

    Chemistry/materials science research

    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
    ádza
    -0.48
    ("
    -0.48
    hip
    -0.42
     quelle
    -0.41
    ador
    -0.40
    amina
    -0.39
    nek
    -0.39
    versal
    -0.39
    line
    -0.39
    dotte
    -0.38
    POSITIVE LOGITS
    MLLoader
    0.97
     Numerade
    0.84
    __':
    0.82
    __":
    0.77
    __':
    0.75
    tvguidetime
    0.75
    pidou
    0.75
     estekak
    0.75
     الحره
    0.75
    ::_('
    0.73
    Activations Density 0.090%

    No Known Activations