© 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. 851
    Prev
    Next
    INDEX
    Explanations

    the phrase "level of" followed by a noun or description.

    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
     Rigidbody
    -0.82
    numerusform
    -0.76
     Gorman
    -0.72
    poem
    -0.68
     OMITBAD
    -0.68
    %)$
    -0.67
    ضم
    -0.67
     Babi
    -0.67
    casse
    -0.67
    }))
    -0.67
    POSITIVE LOGITS
     LEVEL
    2.27
     Level
    2.14
     level
    2.09
    level
    2.09
    LEVEL
    2.06
    Level
    2.03
     Levels
    2.00
     levels
    1.98
    levels
    1.92
    Levels
    1.91
    Activations Density 0.525%

    No Known Activations