© 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. 92623
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Мексичка
    -0.60
    <bos>
    -0.59
     utafitiHapana
    -0.58
    ;"></
    -0.56
     Vikipedi
    -0.54
     to
    -0.53
    extAlignment
    -0.52
    contentLoaded
    -0.51
    liceerd
    -0.50
     NSCoder
    -0.49
    POSITIVE LOGITS
     put
    0.57
     say
    0.52
     mock
    0.51
     suggest
    0.51
     subray
    0.50
     Administrativna
    0.50
     underline
    0.49
     fall
    0.49
     underscore
    0.49
    ScopeManager
    0.49
    Activations Density 0.003%

    No Known Activations