© 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. 4-CLT-HP
    7. 4383
    Prev
    Next
    INDEX
    Explanations

    forward slash

    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
     or
    -0.79
     and
    -0.75
     to
    -0.69
     is
    -0.68
     in
    -0.67
     for
    -0.66
     has
    -0.65
     at
    -0.64
     will
    -0.64
     on
    -0.63
    POSITIVE LOGITS
     Мексичка
    0.90
    NameInMap
    0.89
    webElementXpaths
    0.87
    Personendaten
    0.85
    EndGlobalSection
    0.84
    +#+#
    0.82
     мәкал
    0.81
    contentLoaded
    0.81
     Roskov
    0.80
    تقاوى
    0.79
    Activations Density 0.009%

    No Known Activations