© 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. 24659
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and acknowledgment

    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
    脚注の使い方
    -0.92
     '\\;'
    -0.81
     архивлан
    -0.81
    AndEndTag
    -0.80
     BoxFit
    -0.79
     Мексичка
    -0.79
    parsedMessage
    -0.77
    elemField
    -0.76
    WireFormatLite
    -0.76
     initComponents
    -0.75
    POSITIVE LOGITS
    Builder
    0.45
     Builder
    0.44
    !
    0.42
     please
    0.42
    matig
    0.42
    IRECT
    0.42
     sé
    0.41
    wertung
    0.40
    träglich
    0.40
     millions
    0.39
    Activations Density 0.095%

    No Known Activations