© 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. 1-CLT-HP
    7. 15755
    Prev
    Next
    INDEX
    Explanations

    Hum

    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
     Zeus
    -0.73
    Geplaatst
    -0.68
    Tikang
    -0.57
    ScopeManager
    -0.54
    MockMvc
    -0.54
    Pair
    -0.54
     Gracie
    -0.54
     Pors
    -0.54
     saja
    -0.53
     насељу
    -0.53
    POSITIVE LOGITS
    ming
    0.68
    -------------</
    0.61
    ankind
    0.60
    OMING
    0.57
    theim
    0.55
    mingen
    0.50
    ANNES
    0.46
    ApiModelProperty
    0.46
    DMETHOD
    0.46
    mingbird
    0.46
    Activations Density 0.244%

    No Known Activations