© 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. 92896
    Prev
    Next
    INDEX
    Explanations

    code, date formats

    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
    #+#
    -0.55
     }}"></
    -0.49
    økt
    -0.48
    umah
    -0.48
    ocene
    -0.46
     lois
    -0.46
    appcompat
    -0.46
     Population
    -0.45
     lama
    -0.44
    omed
    -0.44
    POSITIVE LOGITS
     kaarangay
    0.59
     AssemblyCulture
    0.58
    rungsseite
    0.58
    verifyException
    0.57
    adecimal
    0.57
     Réponses
    0.55
    ExtendWith
    0.55
     resourceCulture
    0.54
     ostavi
    0.54
     Roskov
    0.54
    Activations Density 0.000%

    No Known Activations