© 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. 5-CLT-HP
    7. 4633
    Prev
    Next
    INDEX
    Explanations

    is

    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
    __*/
    -0.47
    UTERS
    -0.46
    öd
    -0.46
     跳转至
    -0.45
    gypti
    -0.44
     fed
    -0.43
     credited
    -0.43
     taxed
    -0.43
    strings
    -0.42
     insured
    -0.42
    POSITIVE LOGITS
     jScrollPane
    0.67
    sizeCache
    0.59
    MessageTagHelper
    0.58
    ClientSize
    0.56
     الحره
    0.53
    Tembelea
    0.52
    例句
    0.52
     resourceCulture
    0.51
    SharedDtor
    0.51
     Roskov
    0.51
    Activations Density 0.004%

    No Known Activations