© 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. 93831
    Prev
    Next
    INDEX
    Explanations

    research/named entities

    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
     Anſ
    -0.81
     Diſ
    -0.78
     myſelf
    -0.75
    BibitemShut
    -0.74
     Inſ
    -0.74
     Houſe
    -0.73
     Efq
    -0.71
     fhort
    -0.70
     Majefty
    -0.69
    fible
    -0.68
    POSITIVE LOGITS
    s
    0.82
    a
    0.78
    t
    0.74
    o
    0.73
    e
    0.72
    d
    0.68
    y
    0.66
    n
    0.65
    sy
    0.60
    l
    0.59
    Activations Density 0.049%

    No Known Activations