© 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. 5-CLT-HP
    7. 4368
    Prev
    Next
    INDEX
    Explanations

    priest

    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
    TemporalType
    -0.63
    shund
    -0.54
    asteroide
    -0.54
     baptism
    -0.51
    BeginContext
    -0.50
    ftagPool
    -0.50
    AllAfrica
    -0.50
    getWriter
    -0.49
    Conclusie
    -0.49
    мум
    -0.49
    POSITIVE LOGITS
    enderror
    0.51
     revenus
    0.50
     død
    0.48
    ConstraintMaker
    0.46
     murale
    0.44
    MockBean
    0.44
     where
    0.42
     écrans
    0.42
     lägga
    0.41
     médec
    0.41
    Activations Density 0.002%

    No Known Activations