© 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. 669
    Prev
    Next
    INDEX
    Explanations

    the words "same" and "day" within a short distance of each other, often with a hyphen between them, sometimes also finding "sex".

    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
    oforte
    -0.58
    TRIBUN
    -0.58
     surla
    -0.57
    jsoup
    -0.54
    ustre
    -0.53
    光是
    -0.52
     especially
    -0.51
    __*/
    -0.51
     còn
    -0.51
    rawan
    -0.50
    POSITIVE LOGITS
     exact
    1.03
    exact
    0.93
     EXACT
    0.88
     Exact
    0.88
    EXACT
    0.81
    Exact
    0.79
    Same
    0.78
     Same
    0.76
     same
    0.69
    same
    0.69
    Activations Density 0.572%

    No Known Activations