© 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. 0-CLT-HP
    7. 91074
    Prev
    Next
    INDEX
    Explanations

    actions being performed

    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
     nahilalakip
    -0.98
    GEBURTSDATUM
    -0.96
    rrggbb
    -0.89
    BagConstraints
    -0.86
     FetchType
    -0.86
    styleType
    -0.81
    rungsseite
    -0.81
    ỡng
    -0.80
    IntoConstraints
    -0.79
     transfieras
    -0.77
    POSITIVE LOGITS
    er
    0.56
     transfer
    0.53
     in
    0.53
    es
    0.52
     from
    0.50
     home
    0.49
    ly
    0.49
     its
    0.48
     National
    0.48
     lifetime
    0.47
    Activations Density 0.033%

    No Known Activations