© 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. 73151
    Prev
    Next
    INDEX
    Explanations

    super

    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
    PerformLayout
    -0.66
    principalTable
    -0.53
    ốp
    -0.52
    Parcelize
    -0.52
    qrstuvwxyz
    -0.50
    addContainerGap
    -0.47
    hwar
    -0.46
    Plot
    -0.45
    ToolStripButton
    -0.45
    parseFrom
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.59
    이버
    0.52
     InputDecoration
    0.52
    VersionUID
    0.51
    enumii
    0.51
    ICATED
    0.50
     tie
    0.48
     spike
    0.48
    发表于
    0.46
     Tied
    0.46
    Activations Density 0.001%

    No Known Activations