© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1836
    Prev
    Next
    INDEX
    Explanations

    value

    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
    StoryboardSegue
    -0.56
    OrNil
    -0.56
    GeneratedValue
    -0.54
    randomUUID
    -0.52
     Publicar
    -0.52
     disjoint
    -0.52
    JEL
    -0.51
    ustimmung
    -0.50
     MERCHANTABILITY
    -0.50
     éché
    -0.49
    POSITIVE LOGITS
     ***!
    0.57
     برانيه
    0.53
     ExecuteAsync
    0.52
    setzen
    0.51
    así
    0.50
    __(/*!
    0.49
     >=",
    0.48
    @{
    0.48
     zurück
    0.47
    WindowConstants
    0.47
    Activations Density 0.010%

    No Known Activations