© 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. 91550
    Prev
    Next
    INDEX
    Explanations

    Date and time in news

    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
    MfG
    -0.48
    __/
    -0.47
    cách
    -0.45
    zeptember
    -0.44
     braids
    -0.42
    brides
    -0.42
    upe
    -0.41
    -'
    -0.41
    createObject
    -0.40
    Recreation
    -0.40
    POSITIVE LOGITS
     الحره
    0.80
     tartalomajánló
    0.64
    runApp
    0.56
    oneofs
    0.55
    hbs
    0.55
    WebVitals
    0.55
    viert
    0.54
     виправивши
    0.54
    énario
    0.54
     برانيه
    0.52
    Activations Density 0.001%

    No Known Activations