© 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. 0-CLT-HP
    7. 94968
    Prev
    Next
    INDEX
    Explanations

    stopwords

    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
    httphttps
    -0.60
    proken
    -0.57
    Билгалдахарш
    -0.54
    :✨
    -0.52
     BoxDecoration
    -0.52
    áře
    -0.50
     gynhyrchwyd
    -0.49
    StructEnd
    -0.49
    はじめに
    -0.49
    oneofs
    -0.48
    POSITIVE LOGITS
    -
    0.99
    -$
    0.57
    TemporalType
    0.57
    d
    0.56
    _
    0.55
    -'
    0.50
     című
    0.50
    1
    0.49
    ‑
    0.49
     szüks
    0.47
    Activations Density 0.129%

    No Known Activations