© 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. 2-RES-MATRYOSHKA-DC
    7. 6693
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic or political unit names

    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
     The
    -0.48
     they
    -0.47
     and
    -0.47
     écoulé
    -0.47
     enough
    -0.45
     They
    -0.44
    ritis
    -0.44
     a
    -0.44
    </blockquote>
    -0.44
     It
    -0.44
    POSITIVE LOGITS
     names
    1.47
     pleaſure
    1.22
     surnames
    1.16
     navnet
    1.16
     Anſ
    1.07
     myſelf
    1.05
     Names
    1.05
     houſe
    1.05
    Personendaten
    1.05
     name
    1.04
    Activations Density 0.115%

    No Known Activations