© 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. 94867
    Prev
    Next
    INDEX
    Explanations

    asleep

    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
     Monfieur
    -0.85
    DeleteBehavior
    -0.84
     itſelf
    -0.82
    ViewFeatures
    -0.82
    tonode
    -0.76
    centiles
    -0.76
     BIBSYS
    -0.75
    verifyException
    -0.75
    kháu
    -0.75
     onwards
    -0.74
    POSITIVE LOGITS
    himp
    0.43
    íše
    0.40
     late
    0.40
    ̣ng
    0.38
     volgen
    0.37
    SNMP
    0.37
     niedrig
    0.36
     vroeg
    0.36
    getElements
    0.36
    förs
    0.36
    Activations Density 0.089%

    No Known Activations