© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    :\

    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
     wouldn
    -0.64
    wouldn
    -0.62
     Wouldn
    -0.53
    Would
    -0.48
     would
    -0.45
    Wouldn
    -0.45
     Would
    -0.44
     ادار
    -0.43
    poids
    -0.43
    +:+
    -0.42
    POSITIVE LOGITS
    ^(@)
    0.77
     AssemblyVersion
    0.71
     poffible
    0.68
     traceable
    0.67
    jgl
    0.66
     sensitization
    0.65
     ujednoznacz
    0.65
     متعلقه
    0.63
     Verſ
    0.63
     Theſe
    0.63
    Activations Density 0.025%

    No Known Activations