© 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. 92283
    Prev
    Next
    INDEX
    Explanations

    must

    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
    endforeach
    -0.60
    rrggbb
    -0.49
     omelette
    -0.46
    matorium
    -0.46
    VolleyError
    -0.45
     PicClick
    -0.45
    共和国
    -0.45
    encodeWith
    -0.45
     casual
    -0.45
     Boden
    -0.45
    POSITIVE LOGITS
     be
    0.57
    usepackage
    0.55
    ISupport
    0.52
    ----</
    0.51
    __(/*!
    0.51
     kasarigan
    0.50
    BeginInit
    0.49
    databind
    0.49
     &___
    0.48
     have
    0.48
    Activations Density 0.007%

    No Known Activations