© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91171
    Prev
    Next
    INDEX
    Explanations

    Seeds

    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
    UnknownFields
    -0.71
    -------------</
    -0.71
    Seeds
    -0.64
     Seeds
    -0.60
     Silo
    -0.58
    IUrlHelper
    -0.58
     velkommen
    -0.57
    #
    -0.57
    omnia
    -0.57
     שוליים
    -0.57
    POSITIVE LOGITS
    AndEndTag
    0.82
    WebControls
    0.57
     defaultstate
    0.51
    Geplaatst
    0.50
    AnimationsModule
    0.49
    SPJ
    0.49
    QtWidgets
    0.46
    ########.
    0.46
     ModelExpression
    0.46
    stdc
    0.45
    Activations Density 1.625%

    No Known Activations