© 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. 0-CLT-HP
    7. 93207
    Prev
    Next
    INDEX
    Explanations

    sci

    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
     sci
    -0.68
    sci
    -0.63
     Andaman
    -0.51
    ⊢
    -0.47
     gangen
    -0.46
    చి
    -0.46
     Super
    -0.44
    andaan
    -0.44
    passphrase
    -0.44
    揄
    -0.44
    POSITIVE LOGITS
    Bibliograf
    0.71
    Personendaten
    0.71
    complexContent
    0.67
     kaynağından
    0.66
    ArgumentParser
    0.61
     disambiguazione
    0.61
    WebServlet
    0.57
    الحياه
    0.57
    ंदीखरीदारी
    0.57
    EDEFAULT
    0.53
    Activations Density 1.616%

    No Known Activations