© 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. 72749
    Prev
    Next
    INDEX
    Explanations

    inter

    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
     humaine
    -0.53
    ISPR
    -0.51
    fjspx
    -0.49
     tertawa
    -0.48
     LF
    -0.48
    verifyException
    -0.48
    ilanth
    -0.48
    xFFFFFF
    -0.47
    fromCharCode
    -0.47
     Pich
    -0.46
    POSITIVE LOGITS
    ::_('
    0.55
    //
    0.50
     Audiodateien
    0.49
     SafeMath
    0.49
    MLLoader
    0.49
    UserScript
    0.49
    存于互联网档案馆
    0.47
     dual
    0.47
    पया
    0.47
    tanleria
    0.47
    Activations Density 0.007%

    No Known Activations