© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3237
    Prev
    Next
    INDEX
    Explanations

    School/University

    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
    verifyException
    -0.60
    Hochspringen
    -0.58
    CodeAttribute
    -0.53
    ArrowToggle
    -0.50
    })));
    -0.49
     ConstraintSet
    -0.49
    )))));
    -0.49
     textStatus
    -0.48
    ComponentScan
    -0.47
    ScopeManager
    -0.47
    POSITIVE LOGITS
    <bos>
    0.79
     has
    0.74
     offers
    0.71
    帖最后由
    0.68
     is
    0.66
     invites
    0.65
     provides
    0.64
     had
    0.63
     announces
    0.63
     senior
    0.63
    Activations Density 0.001%

    No Known Activations