© 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. 1-CLT-HP
    7. 15108
    Prev
    Next
    INDEX
    Explanations

    from

    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
    VersionUID
    -0.48
    AndEndTag
    -0.47
     Luzon
    -0.45
     CreateTagHelper
    -0.44
     Exactos
    -0.44
    MessageTagHelper
    -0.44
    észetes
    -0.44
    yarnpkg
    -0.43
    सन्दर्भ
    -0.43
    Portail
    -0.43
    POSITIVE LOGITS
    setw
    0.52
    Tikang
    0.51
    ponym
    0.49
    akei
    0.47
    DELAY
    0.47
    Nonnull
    0.47
    ski
    0.47
    rowable
    0.46
     Fink
    0.46
    Questão
    0.46
    Activations Density 0.021%

    No Known Activations