© 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. 76666
    Prev
    Next
    INDEX
    Explanations

    code strings

    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
    :✨
    -0.86
     Eighth
    -0.84
     eighth
    -0.84
     Seventh
    -0.82
     seventh
    -0.81
     seven
    -0.79
     Seven
    -0.79
    VIAF
    -0.77
    matchCondition
    -0.77
    SharedCtor
    -0.75
    POSITIVE LOGITS
    ４
    0.53
    4
    0.51
    GIVEREF
    0.47
    ⁴
    0.44
    YST
    0.42
    étisme
    0.42
    quatre
    0.42
     löyty
    0.42
    lichung
    0.41
    hammad
    0.41
    Activations Density 0.003%

    No Known Activations