© 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. 3871
    Prev
    Next
    INDEX
    Explanations

    of

    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
    hematics
    -0.57
    RectangleBorder
    -0.51
    kuuta
    -0.51
     doit
    -0.48
    esez
    -0.46
     Must
    -0.45
    atores
    -0.41
    usermodel
    -0.41
    EClass
    -0.40
    enzial
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.71
    ьаж
    0.67
    Predecesor
    0.64
     found
    0.63
     joined
    0.62
    όμε
    0.60
    WebMethod
    0.59
     achieved
    0.57
     preceded
    0.57
     dipilih
    0.56
    Activations Density 0.007%

    No Known Activations