© 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. 0-CLT-HP
    7. 93906
    Prev
    Next
    INDEX
    Explanations

    potential

    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
    TagMode
    -0.81
    Demografía
    -0.68
    OGND
    -0.67
    internalType
    -0.63
     disambiguazione
    -0.63
    ESOME
    -0.60
     OFDb
    -0.56
     aload
    -0.55
     annual
    -0.54
    ี่ยว
    -0.53
    POSITIVE LOGITS
     to
    0.70
     répondu
    0.60
     devenus
    0.56
    PYX
    0.56
     be
    0.52
     refusé
    0.52
     disparu
    0.50
     resté
    0.50
    Tikang
    0.48
    .
    0.48
    Activations Density 0.079%

    No Known Activations