© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11609
    Prev
    Next
    INDEX
    Explanations

    patterns of future expectations and outcomes in narratives

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     resourceCulture
    -0.67
    LookAnd
    -0.67
     /\.
    -0.63
    rrggbb
    -0.62
    VertexAttrib
    -0.58
    ColumnHeaders
    -0.56
     getopt
    -0.55
    "]];
    -0.54
     Corintios
    -0.54
    BaseActivity
    -0.53
    POSITIVE LOGITS
     later
    0.64
    later
    0.60
    EndContext
    0.59
    +:+
    0.58
    utnik
    0.58
    future
    0.57
     future
    0.57
     später
    0.57
    Future
    0.52
     senere
    0.52
    Activations Density 0.087%

    No Known Activations