© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11415
    Prev
    Next
    INDEX
    Explanations

    programming/technical 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
     pitié
    -0.60
     gånger
    -0.55
     rodea
    -0.55
     siker
    -0.54
     spørsmål
    -0.54
     klokken
    -0.54
     magát
    -0.52
     récentes
    -0.51
     voglia
    -0.50
     mijne
    -0.50
    POSITIVE LOGITS
     intptr
    1.07
    ⓧ
    0.81
     [*]
    0.71
     insuffisamment
    0.68
    classnames
    0.64
     Reverso
    0.63
     ProtoMessage
    0.61
    SequentialGroup
    0.61
    EDEFAULT
    0.61
    Personendaten
    0.60
    Activations Density 0.217%

    No Known Activations