© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93639
    Prev
    Next
    INDEX
    Explanations

    references/code

    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
     much
    -0.82
    much
    -0.82
    Much
    -0.77
     Much
    -0.73
     MUCH
    -0.59
    titleMargin
    -0.57
    цездатний
    -0.56
     GenerationType
    -0.56
    NameInMap
    -0.55
    kháu
    -0.55
    POSITIVE LOGITS
    Уважаемые
    0.60
     متعلقه
    0.59
    DockStyle
    0.55
     ejus
    0.53
    ômetro
    0.52
     pleaſure
    0.51
    estris
    0.51
     الحره
    0.51
    micros
    0.50
    TacToe
    0.50
    Activations Density 1.651%

    No Known Activations