© 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. 15859
    Prev
    Next
    INDEX
    Explanations

    SQLite

    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
     disambiguazione
    -0.72
     junta
    -0.62
    GOTREF
    -0.61
     EconPapers
    -0.60
     Beaucoup
    -0.58
     SQLite
    -0.57
    ioutil
    -0.56
    eah
    -0.56
    endphp
    -0.56
     sobri
    -0.55
    POSITIVE LOGITS
    RegressionTest
    0.69
    s
    0.49
     discorso
    0.47
    arita
    0.47
    raš
    0.46
    ervare
    0.45
    zmir
    0.45
     hinweg
    0.44
    allel
    0.43
    žad
    0.43
    Activations Density 0.045%

    No Known Activations