© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43471
    Prev
    Next
    INDEX
    Explanations

    target

    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
     targeting
    -2.42
     targeted
    -2.08
     target
    -2.06
     Targeting
    -2.00
    targeting
    -1.98
     targets
    -1.95
    Target
    -1.90
    targeted
    -1.89
    target
    -1.88
    Targeting
    -1.88
    POSITIVE LOGITS
    zzar
    0.54
     noth
    0.50
     OTO
    0.50
    enumi
    0.47
     febri
    0.47
     Crouch
    0.47
     themſelves
    0.46
     NIA
    0.45
     ་་
    0.45
    DoubleQuotes
    0.45
    Activations Density 0.127%

    No Known Activations