© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    conflicting or contradictory information or accounts

    oai_token-act-pair · gpt-4.1-nano
    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
    WriteLiteral
    -0.81
    DebuggerNonUser
    -0.71
    itanya
    -0.59
    ⓧ
    -0.57
     enx
    -0.57
    SequentialGroup
    -0.56
     lettere
    -0.56
    έα
    -0.55
     mensuales
    -0.54
     LUMP
    -0.54
    POSITIVE LOGITS
     conflicting
    2.58
     contradictory
    1.94
     contradic
    1.00
    licting
    0.98
     противоре
    0.76
     conflicted
    0.69
     препратки
    0.59
     contrasting
    0.57
     incompatible
    0.55
     widers
    0.53
    Activations Density 0.001%

    No Known Activations