© 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. 5-CLT-HP
    7. 93410
    Prev
    Next
    INDEX
    Explanations

    code

    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
    tableFuture
    -0.60
     Odon
    -0.60
    artifactId
    -0.60
    preduce
    -0.57
    WriteAttribute
    -0.57
     bcrypt
    -0.56
    sing
    -0.56
    posedge
    -0.56
    BASEPATH
    -0.55
    yar
    -0.54
    POSITIVE LOGITS
    ata
    0.52
     sociali
    0.51
     malha
    0.48
     honte
    0.47
    maßen
    0.47
     pianta
    0.46
    atisch
    0.45
     flesta
    0.44
     préf
    0.43
    ATA
    0.43
    Activations Density 0.001%

    No Known Activations