© 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. 903
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and memory addresses

    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
     aikana
    -0.59
     näin
    -0.57
    colgroup
    -0.56
     dře
    -0.56
    pinMode
    -0.55
    Референце
    -0.54
     Oficial
    -0.53
     nabíz
    -0.53
     officiels
    -0.52
    b
    -0.52
    POSITIVE LOGITS
     صوتيه
    0.61
    NameInMap
    0.59
    FFFFFF
    0.56
    NOPQRST
    0.54
    FFFF
    0.53
     FFFF
    0.52
     FF
    0.51
     تضيفلها
    0.49
    Diwedd
    0.49
    CCCC
    0.49
    Activations Density 1.377%

    No Known Activations