© 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. 91245
    Prev
    Next
    INDEX
    Explanations

    tree-like structures

    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
    NOPQRST
    -0.62
    RenderAtEndOf
    -0.62
    :+:
    -0.48
    antlr
    -0.46
     mxArray
    -0.46
    alyptus
    -0.43
    break
    -0.42
    tritt
    -0.41
    __',
    -0.41
    Билгалдахарш
    -0.41
    POSITIVE LOGITS
     Nacionales
    0.61
    BeginContext
    0.59
     Gallon
    0.58
    ScopeManager
    0.57
    irão
    0.54
     VOS
    0.54
    ztés
    0.53
    cionario
    0.53
     reprints
    0.53
    الدراسه
    0.53
    Activations Density 0.002%

    No Known Activations