© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93745
    Prev
    Next
    INDEX
    Explanations

    fir

    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
    DoubleQuotes
    -0.68
    ]-->
    -0.59
    AnchorStyles
    -0.58
    providedIn
    -0.57
    );*/
    -0.55
    ElementException
    -0.54
     الحره
    -0.53
     &___
    -0.53
    
    -0.53
    parsedMessage
    -0.50
    POSITIVE LOGITS
     thinning
    0.71
     plantations
    0.68
     plantation
    0.67
    queryInterface
    0.64
     thinned
    0.60
     stumps
    0.58
    FormTagHelper
    0.57
     trees
    0.57
     chainsaw
    0.56
     peat
    0.56
    Activations Density 0.000%

    No Known Activations