© 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. 94336
    Prev
    Next
    INDEX
    Explanations

    Negative and positive conditions

    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
     tri
    -0.70
    RTLD
    -0.54
     entities
    -0.52
    Quest
    -0.51
    日报
    -0.46
    гласно
    -0.46
    ISTICS
    -0.45
    AGAIN
    -0.44
    entities
    -0.44
    lors
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.88
    ChildScrollView
    0.86
    IVEREF
    0.79
    ReusableCell
    0.76
     Económica
    0.72
     <=",
    0.71
     useAppContext
    0.71
     BIBSYS
    0.71
     صوتيه
    0.69
    SaveChangesAsync
    0.68
    Activations Density 1.254%

    No Known Activations