© 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. 4225
    Prev
    Next
    INDEX
    Explanations

    Numbers and/or statistics

    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
     AssemblyTitle
    -0.72
     kasarigan
    -0.69
    abestanden
    -0.65
     périodes
    -0.64
     période
    -0.57
    antaranya
    -0.56
    Period
    -0.55
    featureID
    -0.54
     Periods
    -0.53
    SourceChecksum
    -0.53
    POSITIVE LOGITS
     itinéraires
    0.58
     cumulative
    0.52
     NavController
    0.50
     throws
    0.49
    cirq
    0.49
    χω
    0.47
     Cumulative
    0.47
    tral
    0.47
    ulsory
    0.46
    quelize
    0.46
    Activations Density 0.005%

    No Known Activations