© 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. 3-RES-MATRYOSHKA-DC
    7. 2093
    Prev
    Next
    INDEX
    Explanations

    the words "truth" and "false"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.83
    Архівовано
    -0.70
     InputDecoration
    -0.70
    躇
    -0.63
     consultato
    -0.60
    #+#
    -0.60
     esimer
    -0.60
    DateTimeField
    -0.57
     WaitForSeconds
    -0.57
     '{@
    -0.57
    POSITIVE LOGITS
     truth
    3.23
     Truth
    2.97
    truth
    2.94
    Truth
    2.86
     TRUTH
    2.72
     truths
    2.33
     Wahrheit
    2.19
     Truths
    2.05
     vérité
    2.02
     verità
    1.98
    Activations Density 0.020%

    No Known Activations