© 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. 12-RES-MATRYOSHKA-DC
    7. 10241
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "for" indicating a pattern of conditions or contexts within code or queries

    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
     Púb
    -0.74
    ATN
    -0.60
    Wut
    -0.60
    GetValue
    -0.56
     Coolidge
    -0.55
    NegativeButton
    -0.53
    returnValue
    -0.52
     econômica
    -0.52
     Beweis
    -0.51
    허
    -0.51
    POSITIVE LOGITS
     estimés
    0.78
    "];
    0.75
     lenker
    0.73
     كومونز
    0.72
    "]);
    0.69
    tvguidetime
    0.68
    ")));
    0.67
    ).}
    0.67
    ++);
    0.66
    ]))
    0.66
    Activations Density 0.001%

    No Known Activations