© 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. 1-RES-MATRYOSHKA-DC
    7. 614
    Prev
    Next
    INDEX
    Explanations

    the ability to perform systematic thermodynamic and quantum state optimizations

    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
    \{\\
    -0.69
    vece
    -0.65
    <?,
    -0.64
     CreateTagHelper
    -0.62
    \}\\
    -0.61
     tratti
    -0.59
     spørs
    -0.59
     createSprite
    -0.58
     saken
    -0.57
     Chwiliwch
    -0.57
    POSITIVE LOGITS
     allow
    3.69
     Allow
    3.44
    Allow
    3.38
     allowed
    3.33
     allows
    3.31
     allowing
    3.28
    allow
    3.27
     ALLOW
    3.25
     Allowing
    3.23
    allowing
    3.00
    Activations Density 0.692%

    No Known Activations