© 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. 0-RES-MATRYOSHKA-DC
    7. 12136
    Prev
    Next
    INDEX
    Explanations

    expressions of intent to perform an action

    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
     into
    -0.76
     from
    -0.68
     by
    -0.66
    Pozri
    -0.65
    delijk
    -0.63
     both
    -0.63
     ".";
    -0.63
     upon
    -0.59
     through
    -0.58
     atas
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.88
    SOUNDBITE
    0.84
    RectangleBorder
    0.81
     bezeichneter
    0.81
     betweenstory
    0.79
    contentLoaded
    0.76
    modelBuilder
    0.75
    parsedMessage
    0.68
     مشين
    0.68
    Personendaten
    0.66
    Activations Density 0.338%

    No Known Activations