© 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. 20-CLT-HP
    7. 77287
    Prev
    Next
    INDEX
    Explanations

    bio

    np_max-act-logits · 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
    SPATH
    -0.58
    CPtr
    -0.50
    patra
    -0.46
    getFirstName
    -0.45
     decline
    -0.45
    fare
    -0.44
    ControllerAdvice
    -0.43
     Me
    -0.43
     round
    -0.43
    الحياه
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.68
    ReusableCell
    0.63
    protoimpl
    0.60
     uLocal
    0.57
    forName
    0.54
    jsdelivr
    0.54
     dAtA
    0.53
    miral
    0.53
     pinulongan
    0.53
    Máy
    0.51
    Activations Density 0.003%

    No Known Activations