© 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. 12-RES-MATRYOSHKA-DC
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    sentences expressing encouragement and emotional connection regarding personal experiences

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.54
    ախ
    -0.47
    Datuak
    -0.47
     समीक्षाएं
    -0.45
     poster
    -0.45
    hláš
    -0.44
     living
    -0.43
    ::::::::
    -0.43
    UnitTesting
    -0.42
    MPN
    -0.42
    POSITIVE LOGITS
     initComponents
    0.71
    saraba
    0.67
    IContainer
    0.64
     convite
    0.62
     Offered
    0.60
     للاسماء
    0.59
    ειτουργ
    0.59
    rrggbb
    0.58
     unsolicited
    0.58
    SharedDtor
    0.58
    Activations Density 0.875%

    No Known Activations