© 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. 5-CLT-HP
    7. 2031
    Prev
    Next
    INDEX
    Explanations

    promising

    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
     Roskov
    -1.01
    SourceChecksum
    -0.91
     referenties
    -0.89
    DebuggerNonUser
    -0.81
     Мексичка
    -0.81
     propOrder
    -0.80
     GenerationType
    -0.79
    TagMode
    -0.77
     HasFactory
    -0.75
    SPATH
    -0.75
    POSITIVE LOGITS
    ,
    0.61
     and
    0.57
    ofold
    0.54
    ing
    0.50
    uccio
    0.47
     insuffisamment
    0.46
     stuff
    0.46
    Rendez
    0.46
     capas
    0.42
     Stuff
    0.41
    Activations Density 0.001%

    No Known Activations