© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 553
    Prev
    Next
    INDEX
    Explanations

    phrases related to determination or decision-making processes

    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
     “
    -0.86
     
    -0.78
     ‘
    -0.72
    gäng
    -0.71
     have
    -0.65
     Ha
    -0.63
     ha
    -0.63
    <strong>
    -0.62
     ges
    -0.62
     go
    -0.61
    POSITIVE LOGITS
     Determines
    1.48
     determinations
    1.41
     Determining
    1.40
    Determine
    1.39
     Determination
    1.34
     Determined
    1.34
     Majefty
    1.34
     Efq
    1.34
     détermination
    1.34
     Reſ
    1.33
    Activations Density 0.114%

    No Known Activations