© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97700
    Prev
    Next
    INDEX
    Explanations

    Insurance/business

    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
    annual
    -0.98
     annual
    -0.94
    Annual
    -0.84
     Annual
    -0.78
     ANNUAL
    -0.69
     jähr
    -0.64
    ANNUAL
    -0.62
    iron
    -0.62
    efficient
    -0.58
     iron
    -0.55
    POSITIVE LOGITS
    
    0.77
     незавершена
    0.68
    istic
    0.68
    ness
    0.66
     Mesopo
    0.64
    SPATH
    0.63
    JNIEnv
    0.63
    isation
    0.62
    legi
    0.61
    ised
    0.61
    Activations Density 0.213%

    No Known Activations