© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42294
    Prev
    Next
    INDEX
    Explanations

    detection

    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
     مرئيه
    -0.95
    ico
    -0.85
     detection
    -0.82
     Fair
    -0.74
    IsContent
    -0.71
     burial
    -0.71
    
    -0.66
     صوتيه
    -0.66
    الإنجليزية
    -0.65
    ]--;
    -0.65
    POSITIVE LOGITS
    e
    0.62
    Rates
    0.56
    ksessa
    0.53
     Rates
    0.53
     of
    0.52
     mergeFrom
    0.51
    al
    0.49
    RefNanny
    0.48
     rates
    0.47
    taxia
    0.47
    Activations Density 0.251%

    No Known Activations