© 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. 1-CLT-HP
    7. 10206
    Prev
    Next
    INDEX
    Explanations

    introductory text

    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
    colgroup
    -0.59
     ivelany
    -0.56
    InitStruct
    -0.55
     resourceCulture
    -0.52
    ppu
    -0.50
    hyrchwyd
    -0.49
     imageNamed
    -0.49
    TagHelpers
    -0.49
    ModelForm
    -0.48
     defStyle
    -0.48
    POSITIVE LOGITS
     Baillargeon
    0.56
    ​—
    0.49
    <bos>
    0.48
    Numerology
    0.48
     warmth
    0.47
    EndContext
    0.47
     doubtnut
    0.47
    ￡
    0.47
    uito
    0.47
    
    0.46
    Activations Density 0.009%

    No Known Activations