© 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. 6-RES-MATRYOSHKA-DC
    7. 52
    Prev
    Next
    INDEX
    Explanations

    words that indicate importance or usefulness

    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
     Majefty
    -0.79
     magari
    -0.75
    onAttach
    -0.73
    AndEndTag
    -0.73
    tdessen
    -0.72
     betweenstory
    -0.70
     ModelExpression
    -0.68
    expandindo
    -0.67
     myſelf
    -0.66
     modelAndView
    -0.65
    POSITIVE LOGITS
     very
    0.90
     enough
    0.78
     quite
    0.71
     much
    0.67
     extremely
    0.65
     easy
    0.64
     greatly
    0.64
     pretty
    0.61
     also
    0.60
     מאוד
    0.59
    Activations Density 11.395%

    No Known Activations