© 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. 93941
    Prev
    Next
    INDEX
    Explanations

    pavement

    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
    stand
    -0.66
     tartalomajánló
    -0.63
    unic
    -0.60
    idän
    -0.60
     canst
    -0.59
    Stand
    -0.58
    PerformLayout
    -0.58
    ſelves
    -0.57
     FormControl
    -0.57
    aine
    -0.57
    POSITIVE LOGITS
    最快更新
    0.49
     masses
    0.48
    AppMethodBeat
    0.46
    APOLIS
    0.46
    Referències
    0.45
    mbals
    0.44
     estimés
    0.43
    γραφία
    0.43
    ntag
    0.42
     العام
    0.41
    Activations Density 0.036%

    No Known Activations