© 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. 1-CLT-HP
    7. 15784
    Prev
    Next
    INDEX
    Explanations

    weight-related

    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
     autorytatywna
    -0.67
     виправивши
    -0.65
    ThroughAttribute
    -0.56
    }$}
    -0.54
     Superhost
    -0.54
     الحره
    -0.53
     كومونز
    -0.53
    )')
    -0.53
    jooq
    -0.53
    ">"
    -0.52
    POSITIVE LOGITS
    saraba
    0.56
     efforts
    0.53
    alignSelf
    0.52
     térmico
    0.51
     progress
    0.50
    jectures
    0.50
    zucker
    0.50
    μφωνα
    0.49
     plans
    0.49
     results
    0.48
    Activations Density 0.034%

    No Known Activations