Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12636
    Prev
    Next
    INDEX
    Explanations

    code

    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
    roe
    -1.45
     roe
    -0.63
    roc
    -0.63
    acti
    -0.60
    ROE
    -0.59
    Roe
    -0.57
    torem
    -0.56
     Activate
    -0.54
     activer
    -0.52
    acor
    -0.52
    POSITIVE LOGITS
    RectangleBorder
    0.71
     للاسماء
    0.68
    ंदीखरीदारी
    0.58
     hansen
    0.56
     bless
    0.56
    bless
    0.54
     OnInit
    0.54
     useParams
    0.52
     ElementRef
    0.52
    getJSONArray
    0.51
    Activations Density 0.010%

    No Known Activations