© 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. 15551
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight collaborative behavior and team dynamics in a leadership context

    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
    تقاوى
    -1.08
    ScopeManager
    -1.05
     ProtoMessage
    -0.98
     дописавши
    -0.94
    +#+#
    -0.94
     TextInputType
    -0.94
     Wikimedijinoj
    -0.93
    +#+
    -0.92
     autorytatywna
    -0.90
    AnchorStyles
    -0.89
    POSITIVE LOGITS
    ↵
    0.53
    ...
    0.52
    .
    0.49
     i
    0.48
    jén
    0.47
     I
    0.45
     ved
    0.44
    undang
    0.43
     discriminación
    0.42
     [
    0.42
    Activations Density 0.016%

    No Known Activations