© 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. 93958
    Prev
    Next
    INDEX
    Explanations

    cause and effect

    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
     antaranya
    -0.74
    󠁴
    -0.70
     שוליים
    -0.67
     surla
    -0.66
     complètes
    -0.66
     Gnade
    -0.65
    SequentialGroup
    -0.65
     détect
    -0.65
     identifiés
    -0.64
    RTSC
    -0.64
    POSITIVE LOGITS
     CreateTagHelper
    0.56
     by
    0.51
    tagext
    0.49
     mia
    0.46
     oleh
    0.44
    ടു
    0.43
     my
    0.43
    </em>
    0.43
     our
    0.42
    ˌ
    0.40
    Activations Density 0.270%

    No Known Activations