© 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. 94555
    Prev
    Next
    INDEX
    Explanations

    bral

    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
    writeFieldEnd
    -0.62
    bow
    -0.60
    WI
    -0.57
    ForRow
    -0.56
    buk
    -0.54
    bu
    -0.54
    #+#
    -0.54
     scoper
    -0.53
     HasFactory
    -0.52
     kasarigan
    -0.51
    POSITIVE LOGITS
     Extragalactic
    0.69
     ligiloj
    0.67
     betweenstory
    0.65
    Filmografia
    0.64
     utafitiHapana
    0.61
    Personensuche
    0.60
    IonicModule
    0.60
     surla
    0.60
    Filmografie
    0.59
     indisponible
    0.56
    Activations Density 0.088%

    No Known Activations