© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2827
    Prev
    Next
    INDEX
    Explanations

    avadoc

    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
     surprise
    -0.51
    ROL
    -0.51
    íncipe
    -0.50
     Rohr
    -0.50
    OfDay
    -0.49
    derm
    -0.48
    eait
    -0.48
    andina
    -0.47
    负
    -0.47
    avan
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    Geplaatst
    0.74
     NSCoder
    0.73
    HasBeenSet
    0.71
     JpaRepository
    0.69
    featureID
    0.69
     poffe
    0.68
     ſche
    0.68
    HideFlags
    0.66
    Datuak
    0.66
    Activations Density 0.020%

    No Known Activations