© 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. 22-RES-MATRYOSHKA-DC
    7. 2657
    Prev
    Next
    INDEX
    Explanations

    the word "communication" and its variants

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     ModelExpression
    -0.71
    mybatisplus
    -0.59
     صوتيه
    -0.58
     hefyd
    -0.57
     accordé
    -0.57
    RunAsync
    -0.57
    bership
    -0.52
    وفاته
    -0.51
    ocracy
    -0.51
    ortium
    -0.51
    POSITIVE LOGITS
     communications
    0.73
    \|^{
    0.71
     communication
    0.68
     channels
    0.66
     Communication
    0.65
     Communications
    0.65
     communic
    0.65
     Communicating
    0.64
    Communications
    0.64
     between
    0.62
    Activations Density 0.036%

    No Known Activations