© 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. 38872
    Prev
    Next
    INDEX
    Explanations

    Names, organizations, code

    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
    Hochspringen
    -0.75
    s
    -0.74
     Técnica
    -0.69
    AutoresizingMask
    -0.68
    n
    -0.66
    d
    -0.65
    SHIRE
    -0.65
    shire
    -0.63
     Consortium
    -0.62
    Personendaten
    -0.62
    POSITIVE LOGITS
    IActionResult
    0.56
    ,
    0.53
    Identyfik
    0.49
     she
    0.48
     correctes
    0.48
    tokens
    0.46
    évaluateur
    0.46
     aqu
    0.45
     invokingState
    0.44
     don
    0.43
    Activations Density 0.187%

    No Known Activations