© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    proton

    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
    VersionUID
    -0.56
     صوتيه
    -0.54
    TacToe
    -0.48
    さまで
    -0.45
     يتيمه
    -0.43
    址
    -0.42
    utación
    -0.41
     gouvernements
    -0.41
    waard
    -0.41
     وسلم
    -0.41
    POSITIVE LOGITS
     Shakspeare
    0.66
     Houſe
    0.66
    /**
    0.64
     Monfieur
    0.62
     Majefty
    0.61
     and
    0.60
     houſe
    0.59
     Cæsar
    0.59
     initComponents
    0.57
    BuildContext
    0.57
    Activations Density 0.275%

    No Known Activations