© 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. 14972
    Prev
    Next
    INDEX
    Explanations

    Requirements

    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
    needed
    -0.74
     Needed
    -0.72
     needed
    -0.70
     diperlukan
    -0.68
    necessary
    -0.68
     necesitamos
    -0.65
     besoin
    -0.63
     necessary
    -0.62
     szükséges
    -0.62
     precisamos
    -0.61
    POSITIVE LOGITS
    ValueStyle
    0.58
     Efq
    0.52
    óság
    0.51
    ايا
    0.49
     reg
    0.48
     autorytatywna
    0.48
     Kieran
    0.46
    AddHtmlAttribute
    0.46
     sele
    0.46
     Wikimedijinoj
    0.46
    Activations Density 0.036%

    No Known Activations