© 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. 5-CLT-HP
    7. 92322
    Prev
    Next
    INDEX
    Explanations

    Medical/Scientific text

    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
    spaceBetween
    -0.57
     bands
    -0.53
     band
    -0.50
     trained
    -0.49
    KeySpec
    -0.49
    insics
    -0.48
    нець
    -0.48
     bones
    -0.47
     joints
    -0.46
     implanted
    -0.45
    POSITIVE LOGITS
    ruptedException
    0.71
    __(/*!
    0.66
    
    0.61
    filer
    0.59
    idopsis
    0.59
    (!__
    0.58
    providedIn
    0.58
    idamente
    0.58
    ishly
    0.56
    otry
    0.56
    Activations Density 0.033%

    No Known Activations