© 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. 5-CLT-HP
    7. 95091
    Prev
    Next
    INDEX
    Explanations

    Code and legal text

    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
     发表于
    -0.46
     bề
    -0.41
    Erreferentziak
    -0.37
    $
    -0.36
     Brian
    -0.36
    resizingMask
    -0.36
    ắn
    -0.36
    sil
    -0.35
     hư
    -0.35
     plugging
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.91
     autorytatywna
    0.85
    aarrggbb
    0.83
     دیکھیے
    0.71
     kasarigan
    0.69
     gynhyrchwyd
    0.68
    ViewImports
    0.66
    rungsseite
    0.66
    enumi
    0.66
     Reſ
    0.66
    Activations Density 0.005%

    No Known Activations