© 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. 98048
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    存于互联网档案馆
    -0.58
    MENAFN
    -0.58
    ChildScrollView
    -0.58
     disambiguazione
    -0.53
     Audiodateien
    -0.50
    ագրություններ
    -0.49
    estinal
    -0.48
     AUSSI
    -0.48
     BrowserModule
    -0.47
    Hauptartikel
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.59
     pulumi
    0.53
    vician
    0.51
    Personensuche
    0.51
    FormBorderStyle
    0.50
    NOPQRST
    0.50
     Reverso
    0.50
    FunctionFlags
    0.48
     EconPapers
    0.47
     uLocal
    0.47
    Activations Density 0.001%

    No Known Activations