© 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. 93998
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    cet
    -0.99
     Efq
    -0.68
     gonna
    -0.59
     biceps
    -0.55
    homonymie
    -0.53
    AID
    -0.52
     circulaire
    -0.52
    prefixer
    -0.51
    yntaxException
    -0.50
    windowFixed
    -0.50
    POSITIVE LOGITS
     استنادى
    0.54
    държа
    0.52
    licans
    0.52
    otide
    0.52
     متعلقه
    0.52
    Lmfao
    0.52
     صوتيه
    0.51
    ínia
    0.51
    днев
    0.51
     OFDb
    0.51
    Activations Density 0.146%

    No Known Activations