© 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. 3-RES-MATRYOSHKA-DC
    7. 2479
    Prev
    Next
    INDEX
    Explanations

    html code for a section

    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
     Efq
    -1.13
     itſelf
    -1.05
     myſelf
    -1.04
     Monfieur
    -0.95
     ſhe
    -0.95
     becauſe
    -0.93
     houſe
    -0.91
     poffe
    -0.90
     Eſ
    -0.90
     uſe
    -0.88
    POSITIVE LOGITS
    section
    1.73
    subsection
    1.41
    subsubsection
    1.20
    footer
    0.79
    出版年
    0.59
    idł
    0.56
    IsContent
    0.55
    buttonShape
    0.50
    })));
    0.49
    filepath
    0.48
    Activations Density 0.009%

    No Known Activations