© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    someone giving a review of movies

    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
    +:+
    -0.65
     uska
    -0.55
     oprot
    -0.53
     filming
    -0.51
     BrowserModule
    -0.51
     photographed
    -0.50
     drama
    -0.50
     film
    -0.49
     starred
    -0.48
     thriller
    -0.47
    POSITIVE LOGITS
     animation
    1.65
     animator
    1.49
     Animation
    1.45
     animated
    1.45
     animating
    1.44
     anim
    1.43
     animations
    1.38
     animación
    1.34
     animate
    1.34
    Animation
    1.31
    Activations Density 0.124%

    No Known Activations