© 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. 18-RES-MATRYOSHKA-DC
    7. 761
    Prev
    Next
    INDEX
    Explanations

    storylike synopses with character names and situations involving high stakes, such as those found on the back of book covers

    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.18.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.18.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
     समीक्षाओं
    -0.73
     geweest
    -0.73
     tslint
    -0.68
     myself
    -0.65
     frontale
    -0.65
     zustand
    -0.64
     démocr
    -0.63
     sentí
    -0.63
     bénévoles
    -0.63
     reprezenta
    -0.62
    POSITIVE LOGITS
     discovers
    0.86
     learns
    0.77
     subplot
    0.76
     plot
    0.71
     revenge
    0.71
     secret
    0.69
     flashbacks
    0.68
     secrets
    0.68
     mysterious
    0.67
     flashback
    0.67
    Activations Density 1.533%

    No Known Activations