© 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. 77387
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     surla
    -0.68
     متعلقه
    -0.65
    alignSelf
    -0.55
    ècie
    -0.53
    原始内容存档于
    -0.52
    readInt
    -0.49
    NewReader
    -0.48
    retmen
    -0.47
    stdc
    -0.46
    \{\\
    -0.46
    POSITIVE LOGITS
     two
    1.52
     one
    1.31
     three
    1.18
    two
    1.10
     deux
    1.09
     TWO
    1.07
     ONE
    0.96
     four
    0.94
     één
    0.91
     multiple
    0.90
    Activations Density 0.000%

    No Known Activations