© 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. 45184
    Prev
    Next
    INDEX
    Explanations

    code and documentation

    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
     pew
    -0.90
    pew
    -0.48
     Series
    -0.47
     serie
    -0.45
     den
    -0.43
     Den
    -0.43
     consultato
    -0.43
     series
    -0.43
    Series
    -0.42
    cope
    -0.42
    POSITIVE LOGITS
     itſelf
    1.07
     myſelf
    1.01
    +#+#
    0.94
     Monfieur
    0.90
     raiſ
    0.88
     themſelves
    0.86
     purpoſe
    0.85
     pleaſure
    0.85
     himſelf
    0.85
     perſon
    0.81
    Activations Density 0.906%

    No Known Activations