© 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. 5673
    Prev
    Next
    INDEX
    Explanations

    positive attributes

    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
    ManyToOne
    -0.63
    (),
    -0.62
    WebElementEntity
    -0.56
    ")){
    -0.56
    volent
    -0.54
    "}")
    -0.53
    ASING
    -0.53
    ΑΣ
    -0.53
    альной
    -0.52
    ">#
    -0.52
    POSITIVE LOGITS
     vPvB
    0.59
     ejus
    0.55
     cavalli
    0.54
     ब्रेकडाउन
    0.54
     that
    0.52
    exitRule
    0.52
    WriteTagHelper
    0.51
    .
    0.50
     LEYENDO
    0.50
    SharedDtor
    0.49
    Activations Density 0.002%

    No Known Activations