© 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. 12553
    Prev
    Next
    INDEX
    Explanations

    indicators of incomplete or faulty connections or configurations

    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
    AddTagHelper
    -0.78
    ValueStyle
    -0.61
    ();)
    -0.59
    ContentAlignment
    -0.50
    tituzione
    -0.50
    reszcie
    -0.50
    hots
    -0.50
    principalColumn
    -0.50
     unsus
    -0.49
     Vlas
    -0.49
    POSITIVE LOGITS
     incomplete
    2.25
     Incomplete
    2.11
    incomplete
    2.06
    Incomplete
    1.93
     incomp
    1.36
     unfinished
    1.27
    unfinished
    1.20
     incomplète
    1.05
    rungsseite
    0.91
     imperfect
    0.81
    Activations Density 0.001%

    No Known Activations