© 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. 92083
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     entanto
    -1.08
    tvguidetime
    -0.91
     Мексичка
    -0.91
     larmes
    -0.89
     Савезне
    -0.89
    antaranya
    -0.88
     myſelf
    -0.88
    kään
    -0.85
    ltä
    -0.85
     lèvres
    -0.85
    POSITIVE LOGITS
     this
    0.84
     the
    0.71
     in
    0.67
     it
    0.63
     if
    0.63
    ,
    0.61
     did
    0.60
     there
    0.59
     after
    0.58
     like
    0.57
    Activations Density 0.018%

    No Known Activations