© 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. 93600
    Prev
    Next
    INDEX
    Explanations

    unincorporated

    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
     hospitales
    -0.52
     efficaces
    -0.43
     einges
    -0.43
     tör
    -0.43
     Wikiseite
    -0.43
    expandindo
    -0.41
     duquel
    -0.41
     kän
    -0.40
     respectivas
    -0.40
    abay
    -0.40
    POSITIVE LOGITS
    WithIOException
    0.68
    InitVars
    0.65
     defaultstate
    0.64
    contentLoaded
    0.63
     Sold
    0.62
    -------
    0.61
     Himmels
    0.60
    EDEFAULT
    0.60
    RTLD
    0.59
     opérés
    0.59
    Activations Density 0.002%

    No Known Activations