© 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. 95258
    Prev
    Next
    INDEX
    Explanations

    Generations

    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
     grand
    -0.90
    grand
    -0.66
     grandiose
    -0.65
     Jr
    -0.62
     grandeur
    -0.62
    yntaxException
    -0.60
     grande
    -0.54
     grands
    -0.50
    cesis
    -0.46
     junior
    -0.45
    POSITIVE LOGITS
     مشين
    0.91
     purpoſe
    0.81
     leaſt
    0.80
     ſeveral
    0.77
     Monfieur
    0.74
     Jefus
    0.73
    VERTISEMENT
    0.73
     themſelves
    0.73
    ised
    0.72
     myſelf
    0.71
    Activations Density 0.045%

    No Known Activations