© 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. 24-RES-MATRYOSHKA-DC
    7. 199
    Prev
    Next
    INDEX
    Explanations

    the letter "A" at the beginning of words or abbreviations, often associated with names or organizations

    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.24.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.24.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
    m
    -0.75
    queles
    -0.72
    quilo
    -0.70
    n
    -0.69
    d
    -0.67
    quela
    -0.65
    g
    -0.64
    t
    -0.59
     affrontare
    -0.56
    r
    -0.56
    POSITIVE LOGITS
     few
    0.61
    aaaa
    0.55
    verages
    0.54
    aaa
    0.52
    aaaaaaaa
    0.52
     Few
    0.51
    aaaaa
    0.51
    aaaaaa
    0.48
     lot
    0.47
     little
    0.47
    Activations Density 0.929%

    No Known Activations