© 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. 2458
    Prev
    Next
    INDEX
    Explanations

    first-person narratives involving emotions and interactions with others

    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
     we
    -0.83
     us
    -0.81
     irse
    -0.79
     quedarse
    -0.73
     We
    -0.72
     nous
    -0.71
    We
    -0.68
     ponerse
    -0.63
     adaptarse
    -0.60
     moverse
    -0.59
    POSITIVE LOGITS
     myself
    3.06
     my
    2.72
    myself
    2.33
     mijn
    2.17
    my
    2.11
    我的
    1.95
     meinem
    1.95
     myſelf
    1.91
     minha
    1.89
     meus
    1.88
    Activations Density 1.391%

    No Known Activations