© 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. 106
    Prev
    Next
    INDEX
    Explanations

    clusters of digits, and some hyphens

    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
    KommentareTeilen
    -0.56
     contenus
    -0.52
    APTER
    -0.52
     quatre
    -0.49
     impré
    -0.49
    ɚ
    -0.48
     cinq
    -0.47
    bkz
    -0.47
    ουσ
    -0.46
    __((
    -0.46
    POSITIVE LOGITS
    9
    1.49
    0
    1.45
    7
    1.45
    2
    1.43
    3
    1.43
    8
    1.42
    6
    1.41
    4
    1.40
    1
    1.39
    5
    1.36
    Activations Density 4.416%

    No Known Activations