© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    phrases related to choices and decisions

    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
    ::$_
    -0.73
     didReceive
    -0.66
    gale
    -0.66
    XmlType
    -0.59
     Thoma
    -0.57
    ourable
    -0.56
    خخ
    -0.56
    plant
    -0.55
    มาะ
    -0.55
    Tung
    -0.54
    POSITIVE LOGITS
     Bhatt
    0.83
    SequentialGroup
    0.78
     Comprometido
    0.76
     oop
    0.75
    fjspx
    0.70
     PAZ
    0.68
    MemoryWarning
    0.67
    yszer
    0.64
    ANDUM
    0.64
    enegro
    0.63
    Activations Density 0.029%

    No Known Activations