© 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. 20-CLT-HP
    7. 77107
    Prev
    Next
    INDEX
    Explanations

    Code and technical manuals

    np_max-act-logits · 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
    IGraphics
    -0.57
    ISupport
    -0.56
    !*\
    -0.50
    انظر
    -0.47
     везе
    -0.47
     Rue
    -0.45
    سته
    -0.44
    __*/
    -0.44
    Rè
    -0.43
    älte
    -0.43
    POSITIVE LOGITS
    +#+#
    0.59
    UnusedPrivate
    0.58
    ChildIndex
    0.55
     Diakses
    0.54
     ferons
    0.51
     pressione
    0.51
     onBind
    0.50
     Duplex
    0.50
     resourceCulture
    0.50
    ConstraintMaker
    0.49
    Activations Density 0.002%

    No Known Activations