© 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. 5218
    Prev
    Next
    INDEX
    Explanations

    a

    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
    ViewFeatures
    -0.54
     Réponses
    -0.45
     kasarigan
    -0.44
     TestBed
    -0.44
     faptul
    -0.42
    спомина
    -0.42
     how
    -0.42
     πως
    -0.42
    lanie
    -0.41
    LabelTagHelper
    -0.41
    POSITIVE LOGITS
     Normdatei
    0.69
    ContentAsync
    0.64
    StructEnd
    0.60
    ActionCreators
    0.59
     rowspan
    0.56
     BoxDecoration
    0.55
     yawning
    0.55
     NSCoder
    0.54
     groote
    0.54
    存于互联网档案馆
    0.54
    Activations Density 0.000%

    No Known Activations