© 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. 5725
    Prev
    Next
    INDEX
    Explanations

    actions being done/needed

    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
    .*")]
    -0.81
     resourceCulture
    -0.79
    İstinadlar
    -0.70
    CONCLUSION
    -0.67
    CONCLUSIONS
    -0.66
     conclusion
    -0.66
     pinulongan
    -0.65
    /******/
    -0.62
     محفوظة
    -0.62
    HeaderText
    -0.61
    POSITIVE LOGITS
    chul
    0.50
     look
    0.50
     to
    0.47
    globin
    0.43
     einzu
    0.43
    look
    0.42
     dig
    0.42
    dig
    0.42
    ulare
    0.41
    kloped
    0.40
    Activations Density 0.024%

    No Known Activations