© 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. 1821
    Prev
    Next
    INDEX
    Explanations

    words related to fiction, folklore, fantasy, and horror

    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
    TagMode
    -0.59
    MigrationBuilder
    -0.58
     Akismet
    -0.54
    rapnel
    -0.54
    BatchNorm
    -0.51
     getItemCount
    -0.50
    setBold
    -0.50
     newOwner
    -0.50
    brium
    -0.49
    xhtml
    -0.49
    POSITIVE LOGITS
     supernatural
    1.28
     paranormal
    1.23
     mysterious
    1.13
     spooky
    1.13
     mystical
    1.11
     UFO
    1.11
     magical
    1.07
     ghost
    1.04
     demonic
    1.03
     witchcraft
    1.02
    Activations Density 1.792%

    No Known Activations