© 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. 42520
    Prev
    Next
    INDEX
    Explanations

    scales

    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
     scale
    -2.03
     scales
    -2.03
     Scale
    -1.84
     Scales
    -1.80
     SCALE
    -1.59
    Scale
    -1.57
    Scales
    -1.47
    scales
    -1.46
    scale
    -1.40
    SCALE
    -1.32
    POSITIVE LOGITS
     уста
    0.56
     entertainments
    0.56
    prüche
    0.52
     Añade
    0.52
    ondere
    0.52
    Durata
    0.51
     Bir
    0.50
     affirmations
    0.50
     bará
    0.50
     Flach
    0.50
    Activations Density 0.071%

    No Known Activations