Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 295
    Prev
    Next
    INDEX
    Explanations

    truth

    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
     truth
    -3.25
    truth
    -2.53
     truths
    -2.22
     Truth
    -2.16
     TRUTH
    -2.11
    Truth
    -2.08
     vérité
    -1.91
     Wahrheit
    -1.90
     verità
    -1.84
     verdad
    -1.79
    POSITIVE LOGITS
    y
    0.66
     to
    0.62
    fulness
    0.60
    ,
    0.60
    .
    0.59
    le
    0.58
    k
    0.58
    maker
    0.57
    te
    0.56
     
    0.54
    Activations Density 0.033%

    No Known Activations