© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 2667
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of the verb "lie" and closely related words

    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
    évaluateur
    -0.63
    entrySet
    -0.60
    Fif
    -0.56
     choo
    -0.54
     Bradbury
    -0.54
     gynhyrchwyd
    -0.54
    一抹
    -0.53
    anaf
    -0.53
     McF
    -0.53
     McCl
    -0.52
    POSITIVE LOGITS
     lie
    3.09
     lies
    2.92
     lying
    2.56
     Lies
    2.39
     Lie
    2.36
     Lying
    2.31
    Lying
    2.23
     LIE
    2.22
    Lies
    2.22
    Lie
    2.16
    Activations Density 0.031%

    No Known Activations