© 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. 42657
    Prev
    Next
    INDEX
    Explanations

    ad

    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
    ad
    -1.06
    a
    -0.92
    ap
    -0.88
    AP
    -0.86
    adi
    -0.76
    AD
    -0.75
    Ad
    -0.73
     AP
    -0.71
    i
    -0.69
    o
    -0.66
    POSITIVE LOGITS
     tartalomajánló
    0.73
    ened
    0.71
    aneous
    0.68
    EOUS
    0.67
    nya
    0.66
    ITICAL
    0.66
    ︎
    0.65
    ship
    0.65
    ylvan
    0.65
    theless
    0.64
    Activations Density 0.506%

    No Known Activations