© 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. 1-CLT-HP
    7. 14478
    Prev
    Next
    INDEX
    Explanations

    program

    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
     <>",
    -0.69
    PreferredItem
    -0.61
     Himo
    -0.57
    /></
    -0.57
     دیکھیے
    -0.55
     Италијани
    -0.54
    |}{}
    -0.53
    _));
    -0.52
    batore
    -0.51
    "]);
    -0.51
    POSITIVE LOGITS
     against
    0.56
     Exer
    0.53
    INSTALLED
    0.52
    hintText
    0.50
     Against
    0.49
    uities
    0.49
    omitempty
    0.49
     Zer
    0.48
    against
    0.48
    panou
    0.48
    Activations Density 0.010%

    No Known Activations