© 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. 5-CLT-HP
    7. 5306
    Prev
    Next
    INDEX
    Explanations

    present tense

    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
    LookAnd
    -0.79
     мәкал
    -0.78
    IGraphics
    -0.64
    Παραπομπές
    -0.64
    UserScript
    -0.62
     Drapeau
    -0.60
    uresti
    -0.58
    يكب
    -0.56
     indisponible
    -0.55
     JpaRepository
    -0.55
    POSITIVE LOGITS
     this
    0.76
    this
    0.65
     right
    0.59
     This
    0.54
     normal
    0.53
     good
    0.52
     هذا
    0.52
    This
    0.51
     low
    0.51
     bad
    0.51
    Activations Density 0.001%

    No Known Activations