© 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. 92027
    Prev
    Next
    INDEX
    Explanations

    website

    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
    ikit
    -0.55
    omyces
    -0.51
    doğan
    -0.49
    roslav
    -0.47
    CreateIndex
    -0.46
    <caption>
    -0.46
    posedge
    -0.46
    reta
    -0.45
    bör
    -0.45
    فار
    -0.45
    POSITIVE LOGITS
     باخ
    0.68
    FormBuilder
    0.60
    Parcelize
    0.57
    featureID
    0.56
    WindowConstants
    0.55
    最快更新
    0.54
     MainAxisSize
    0.52
    Vidite
    0.52
     pulumi
    0.52
     BorderSide
    0.51
    Activations Density 0.007%

    No Known Activations