© 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. 12996
    Prev
    Next
    INDEX
    Explanations

    of

    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
    UpInside
    -0.58
    ohjel
    -0.57
     laajenta
    -0.53
     trident
    -0.53
     CGPA
    -0.52
     triad
    -0.52
     Rudolph
    -0.52
    Zeneca
    -0.52
    %"),
    -0.51
     Grizzlies
    -0.51
    POSITIVE LOGITS
     Italijanski
    0.63
     Normdatei
    0.60
    ніципа
    0.55
    UnusedPrivate
    0.55
     work
    0.54
     Meksiku
    0.53
    modelBuilder
    0.53
    aarrggbb
    0.52
     endeavor
    0.51
    rrggbb
    0.50
    Activations Density 0.029%

    No Known Activations