© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    Dixon

    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
    ussis
    -0.62
    aarrggbb
    -0.61
     TestBed
    -0.61
    navBar
    -0.57
    amerikanischer
    -0.54
    ValueStyle
    -0.53
     AppCompatTheme
    -0.53
     Pend
    -0.52
    entin
    -0.52
     memberId
    -0.52
    POSITIVE LOGITS
    таратура
    0.65
    SuccessListener
    0.54
    AutoField
    0.53
    addPreferredGap
    0.52
    rayage
    0.51
    cheibe
    0.50
     الحره
    0.47
    레스
    0.46
    tagHelperRunner
    0.46
    }>;
    0.46
    Activations Density 0.031%

    No Known Activations