© 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. 5-CLT-HP
    7. 98224
    Prev
    Next
    INDEX
    Explanations

    fact

    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
    fromnode
    -0.57
     bagay
    -0.54
     conmigo
    -0.51
    CodeAttribute
    -0.49
     externi
    -0.49
     Politique
    -0.48
     presentarse
    -0.48
    +};
    -0.47
    <bos>
    -0.47
    ?$
    -0.47
    POSITIVE LOGITS
     Abp
    0.54
    Obrázky
    0.53
     applicants
    0.53
    SuspendLayout
    0.52
     '\\;'
    0.52
     actors
    0.52
     AspNetCore
    0.52
     you
    0.50
     most
    0.49
     Réponses
    0.49
    Activations Density 0.001%

    No Known Activations