© 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. 39890
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    évaluateur
    -0.90
     CreateTagHelper
    -0.88
     nahilalakip
    -0.84
     Akismet
    -0.79
    GOTREF
    -0.78
     мәкал
    -0.73
    afficheront
    -0.73
    horabuena
    -0.73
    MemoryWarning
    -0.72
    exitRule
    -0.72
    POSITIVE LOGITS
    lotto
    0.52
    OTIC
    0.52
     trí
    0.52
     role
    0.51
    lotti
    0.49
     prec
    0.48
     vân
    0.48
     Prompt
    0.47
    zae
    0.47
     signal
    0.47
    Activations Density 0.051%

    No Known Activations