© 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. 9936
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    webElementXpaths
    -0.72
     समीक्षाओं
    -0.69
     pinulongan
    -0.66
     hưởng
    -0.60
    bewerken
    -0.59
    antMatchers
    -0.57
    大利
    -0.57
    jména
    -0.57
     endforeach
    -0.56
     recul
    -0.56
    POSITIVE LOGITS
    insu
    0.46
    erman
    0.44
     BoxFit
    0.43
    ilder
    0.43
    Sprintf
    0.42
     discover
    0.42
    CharStream
    0.42
     dial
    0.41
    DateTimeField
    0.41
    wning
    0.41
    Activations Density 0.214%

    No Known Activations