© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2397
    Prev
    Next
    INDEX
    Explanations

    Dear

    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
     copies
    -0.69
    waltung
    -0.68
    fjspx
    -0.65
     Angew
    -0.65
    umna
    -0.62
     Copies
    -0.61
    lafen
    -0.61
     ſtre
    -0.60
    kehrt
    -0.60
    ilibrium
    -0.60
    POSITIVE LOGITS
    脚注の使い方
    0.58
    LookAnd
    0.49
    rrggbb
    0.46
     nakalista
    0.44
    bewerken
    0.41
    GraphicsUnit
    0.39
    WithIOException
    0.38
    "}";
    0.38
    tvguidetime
    0.37
     ""))
    0.36
    Activations Density 0.004%

    No Known Activations