© 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. 12828
    Prev
    Next
    INDEX
    Explanations

    references to a specific conceptual category, likely related to inadequate or insufficient quality or quantity

    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
    UnknownFieldSet
    -0.65
    loài
    -0.63
    \{\\
    -0.61
    bitol
    -0.61
    AutoScaleMode
    -0.59
    ="@+
    -0.58
     heller
    -0.57
    nocache
    -0.56
    новниш
    -0.54
    Controllo
    -0.54
    POSITIVE LOGITS
     inadequate
    2.08
     inadequacy
    1.69
     Inadequate
    1.52
     inadequ
    1.09
     insufficient
    0.95
     inade
    0.88
    nadequate
    0.84
     insufic
    0.72
     adequacy
    0.65
    >>();
    0.63
    Activations Density 0.001%

    No Known Activations