© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    single quotes

    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
     Menge
    -0.94
    }}"
    -0.90
     $("<
    -0.89
    \""
    -0.88
    {}".
    -0.88
    osoba
    -0.82
     Bartol
    -0.82
     "}
    -0.80
     Bulldogs
    -0.79
    mazoo
    -0.79
    POSITIVE LOGITS
     '
    1.52
     ('
    1.27
     ‘
    1.16
    !='
    1.16
     ='
    1.12
    -'
    1.10
    +'
    1.09
    ='
    1.08
     '.
    1.04
    ('
    1.03
    Activations Density 0.860%

    No Known Activations