© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 814
    Prev
    Next
    INDEX
    Explanations

    ellipsis

    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
     giapp
    -0.53
     étoit
    -0.49
     russes
    -0.48
    they
    -0.48
     république
    -0.47
     pouvoit
    -0.47
     auroit
    -0.47
    ########.
    -0.46
     itſelf
    -0.46
     zijne
    -0.45
    POSITIVE LOGITS
     The
    0.77
     A
    0.76
     To
    0.73
     In
    0.72
     It
    0.71
     For
    0.71
     At
    0.69
     As
    0.69
     Of
    0.67
     And
    0.67
    Activations Density 0.004%

    No Known Activations