© 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. 1-RES-MATRYOSHKA-DC
    7. 1028
    Prev
    Next
    INDEX
    Explanations

    requests for information or instructions to communicate or share knowledge

    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
    XmlAccessorType
    -0.74
    ViewFeatures
    -0.66
     стаття
    -0.61
    ActivityCompat
    -0.52
    PROPOSED
    -0.51
     wireType
    -0.51
     ويكيميديا
    -0.50
    yecek
    -0.50
    ̍t
    -0.50
     cré
    -0.49
    POSITIVE LOGITS
     tell
    4.13
     Tell
    3.86
    Tell
    3.73
     TELL
    3.58
     telling
    3.56
     tells
    3.50
    tell
    3.38
     Telling
    3.36
     told
    3.34
     Tells
    3.20
    Activations Density 0.210%

    No Known Activations