© 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. 2471
    Prev
    Next
    INDEX
    Explanations

    text that describes characters' emotions and reactions

    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
     boredom
    -0.70
     bored
    -0.65
     disambiguazione
    -0.64
     sadness
    -0.63
     melancholy
    -0.61
    κτηρισ
    -0.61
     somber
    -0.60
     irritation
    -0.59
     impatience
    -0.59
    Mood
    -0.59
    POSITIVE LOGITS
     screaming
    0.77
     struggled
    0.76
     struggling
    0.74
     gasping
    0.70
     struggle
    0.69
     screams
    0.69
     screamed
    0.69
     scream
    0.68
     lutte
    0.68
     wri
    0.68
    Activations Density 0.174%

    No Known Activations