© 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. 4-CLT-HP
    7. 928
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    tvguidetime
    -0.67
    Revenir
    -0.66
    脚注の使い方
    -0.65
     CreateTagHelper
    -0.59
     跳转至
    -0.54
     mobilized
    -0.51
    cinated
    -0.47
    cended
    -0.47
     архивлан
    -0.45
    irmed
    -0.44
    POSITIVE LOGITS
    enumii
    0.68
     statement
    0.66
    BeforeClass
    0.64
     Statement
    0.59
     statements
    0.57
    estacks
    0.57
     keyword
    0.57
     operator
    0.56
     Statements
    0.56
    ()
    0.55
    Activations Density 0.172%

    No Known Activations