© 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. 94354
    Prev
    Next
    INDEX
    Explanations

    fold and iron

    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
     iron
    -0.66
    Fe
    -0.55
     universale
    -0.52
     hierro
    -0.50
     secondaires
    -0.49
     Immunology
    -0.48
     Failure
    -0.48
     fold
    -0.48
    insics
    -0.48
    Iron
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.59
     Normdatei
    0.59
     AttributeSet
    0.58
    MLLoader
    0.58
    dafx
    0.56
    providedIn
    0.55
    endphp
    0.55
    Descripció
    0.55
    äiv
    0.54
    gings
    0.53
    Activations Density 0.024%

    No Known Activations