© 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. 20128
    Prev
    Next
    INDEX
    Explanations

    references to camaraderie or companionship

    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
    Annette
    -0.76
     Annette
    -0.73
    pwr
    -0.69
     tarvit
    -0.68
     něko
    -0.66
    stalline
    -0.65
    ranton
    -0.65
     Kanz
    -0.65
    creas
    -0.64
    ricanes
    -0.64
    POSITIVE LOGITS
     Fellows
    1.30
    Fellow
    1.23
     Fellow
    1.21
     FELLOW
    1.20
     Fellowship
    1.00
     Fellowships
    0.99
    fellow
    0.95
     fellow
    0.90
     fellows
    0.88
     fellowship
    0.84
    Activations Density 0.005%

    No Known Activations