© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    the words "another" and "other" followed by words indicating importance or sequence

    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
    tauscht
    -0.54
     кӀ
    -0.51
    Lähteet
    -0.49
    DOCTYPE
    -0.47
    ourced
    -0.43
    Marty
    -0.42
     biên
    -0.41
     dieselben
    -0.41
    paksa
    -0.40
    mere
    -0.40
    POSITIVE LOGITS
     thing
    0.99
     important
    0.97
     noteworthy
    0.91
     interesting
    0.90
     notable
    0.89
     peculiarity
    0.83
     reason
    0.83
     aspect
    0.82
     caveat
    0.81
     tärke
    0.80
    Activations Density 0.696%

    No Known Activations