© 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. 868
    Prev
    Next
    INDEX
    Explanations

    the word "Title" and words surrounding it regardless of context

    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
     Gad
    -0.47
    onshire
    -0.45
    Baca
    -0.41
    READ
    -0.41
    lihat
    -0.40
    DatePicker
    -0.40
    ?>"
    -0.39
    andri
    -0.39
    nett
    -0.39
    aga
    -0.38
    POSITIVE LOGITS
    titles
    1.10
     titles
    1.09
     Titles
    1.09
    Titles
    1.08
     AppComponent
    1.04
     getTitle
    1.00
     TITLE
    0.95
     autorytatywna
    0.94
     AssemblyProduct
    0.93
    OGND
    0.91
    Activations Density 0.178%

    No Known Activations