© 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. 20-CLT-HP
    7. 77683
    Prev
    Next
    INDEX
    Explanations

    Spanish words

    np_max-act-logits · 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
    Hochspringen
    -0.63
    Slf
    -0.60
     EconPapers
    -0.56
     impossibile
    -0.56
    脚注の使い方
    -0.54
    verifyException
    -0.52
    hejiang
    -0.52
    ieteur
    -0.51
    gines
    -0.49
    fycat
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.59
     ujednoznacz
    0.49
    roy
    0.49
    ro
    0.48
    reon
    0.48
    ExtendWith
    0.47
    roh
    0.47
    roj
    0.47
    rosa
    0.45
    UTELY
    0.45
    Activations Density 0.001%

    No Known Activations