© 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. 44098
    Prev
    Next
    INDEX
    Explanations

    increasing

    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
     to
    -0.80
     proposées
    -0.70
     using
    -0.68
     with
    -0.66
     between
    -0.63
     into
    -0.63
     on
    -0.61
     utilizing
    -0.61
     towards
    -0.60
     at
    -0.59
    POSITIVE LOGITS
     number
    0.64
     numerus
    0.61
     trend
    0.59
     series
    0.56
    uxxxx
    0.55
     presence
    0.49
    chengladbach
    0.49
     esternos
    0.49
    umbersome
    0.48
    хьтан
    0.48
    Activations Density 0.086%

    No Known Activations