© 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. 674
    Prev
    Next
    INDEX
    Explanations

    lines of computer code in a variety of languages along with hexadecimal strings

    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
    ly
    -1.49
    に
    -1.31
    了
    -1.15
    nya
    -1.10
    d
    -0.98
    mos
    -0.94
    c
    -0.92
    the
    -0.91
    men
    -0.89
    m
    -0.88
    POSITIVE LOGITS
    heartedly
    0.33
    returning
    0.33
    heights
    0.33
    hook
    0.32
    parents
    0.32
    enough
    0.32
    hooks
    0.31
     dieux
    0.31
     appellants
    0.31
    artificial
    0.31
    Activations Density 2.060%

    No Known Activations