© 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. 92040
    Prev
    Next
    INDEX
    Explanations

    loss

    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
     volna
    -0.54
     ervoor
    -0.52
     short
    -0.48
     väli
    -0.47
     soll
    -0.46
    откры
    -0.46
     dagegen
    -0.46
    oniec
    -0.45
     long
    -0.44
    سری
    -0.44
    POSITIVE LOGITS
     Roskov
    0.90
     متعلقه
    0.85
    Geplaatst
    0.84
    sizeCache
    0.81
    parsedMessage
    0.75
     Italijanski
    0.72
     الرياضيه
    0.69
    oredCriteria
    0.69
    脚注の使い方
    0.68
    WebServlet
    0.68
    Activations Density 0.078%

    No Known Activations