© 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. 38725
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
     Theſe
    -0.96
     ſever
    -0.92
     myſelf
    -0.91
     itſelf
    -0.91
    Datuak
    -0.90
     Houſe
    -0.83
     Anſ
    -0.82
     varandra
    -0.82
     uſed
    -0.82
     houſe
    -0.81
    POSITIVE LOGITS
     of
    0.72
     (
    0.59
     base
    0.57
     "
    0.55
     as
    0.54
    ,
    0.54
     re
    0.53
     and
    0.52
     .
    0.52
     or
    0.52
    Activations Density 0.027%

    No Known Activations