© 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. 0-CLT-HP
    7. 94502
    Prev
    Next
    INDEX
    Explanations

    code and science

    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
    sz
    -0.54
     ſhould
    -0.53
    SizeF
    -0.52
    sala
    -0.51
    apa
    -0.50
    ships
    -0.50
    tencent
    -0.49
    ArrayAdapter
    -0.49
     joaat
    -0.48
     CURIAM
    -0.48
    POSITIVE LOGITS
    verwijspagina
    0.62
    Datuak
    0.60
    errHandler
    0.59
    УДК
    0.59
    Referències
    0.58
    Personendaten
    0.58
     الرياضيه
    0.55
     eventdata
    0.52
    ूह
    0.51
    Enllaços
    0.51
    Activations Density 0.338%

    No Known Activations