© 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. 9531
    Prev
    Next
    INDEX
    Explanations

    notre

    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
    ako
    -2.48
    AKO
    -1.47
     esternos
    -0.64
    Ako
    -0.63
    出版年
    -0.58
    ko
    -0.57
     diputados
    -0.56
     ako
    -0.55
    InstanceState
    -0.54
     locaux
    -0.52
    POSITIVE LOGITS
     AspNetCore
    0.78
     tartalomajánló
    0.61
     Administrativna
    0.60
     ComVisible
    0.59
     otomatig
    0.57
    bonucleic
    0.56
    stdc
    0.54
     linkovi
    0.54
     Bug
    0.54
     Source
    0.54
    Activations Density 0.146%

    No Known Activations