© 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. 20-CLT-HP
    7. 73197
    Prev
    Next
    INDEX
    Explanations

    four/4

    np_max-act-logits · 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
    SharedDtor
    -0.98
    LookAnd
    -0.97
     autorytatywna
    -0.96
    setVerticalGroup
    -0.96
    transQ
    -0.95
    parsedMessage
    -0.82
    WriteBarrier
    -0.82
    awtextra
    -0.81
    DebuggerNonUser
    -0.80
    IUrlHelper
    -0.80
    POSITIVE LOGITS
     own
    0.49
     Four
    0.40
     le
    0.36
    4
    0.35
    Four
    0.35
     place
    0.34
     four
    0.34
    four
    0.34
     propre
    0.33
    ich
    0.32
    Activations Density 0.000%

    No Known Activations