© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    of

    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
     a
    -0.64
    ).'
    -0.52
     an
    -0.52
    ).”
    -0.52
    )”.
    -0.51
    "%(
    -0.51
     ').
    -0.50
     '
    -0.50
    @",
    -0.50
    them
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.77
     enfans
    0.73
     armée
    0.66
     étoient
    0.65
    matchCondition
    0.60
    таратура
    0.60
    ValueStyle
    0.59
     the
    0.59
     plufieurs
    0.59
    rungsseite
    0.58
    Activations Density 0.006%

    No Known Activations