© 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. 45743
    Prev
    Next
    INDEX
    Explanations

    some

    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
     disambiguazione
    -1.16
     defaultstate
    -0.85
    CloseOperation
    -0.82
     препратки
    -0.80
     الحره
    -0.78
     >=",
    -0.77
     kaynağından
    -0.77
     otomatig
    -0.77
     linkovi
    -0.76
     виправивши
    -0.75
    POSITIVE LOGITS
     
    0.73
     $
    0.56
    '],$
    0.46
    top
    0.39
    ']=$
    0.38
    "=>$
    0.38
    romptu
    0.36
     бывает
    0.35
     everyday
    0.35
     Stillwater
    0.34
    Activations Density 0.009%

    No Known Activations