© 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. 12-RES-MATRYOSHKA-DC
    7. 28400
    Prev
    Next
    INDEX
    Explanations

    instances of graphical or data representation formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     Duckworth
    -0.88
    httphttps
    -0.83
    conomie
    -0.82
    发表于
    -0.79
     חיצוניים
    -0.79
     Drury
    -0.79
    djangoproject
    -0.79
    displayquote
    -0.79
     Huck
    -0.78
    apunov
    -0.77
    POSITIVE LOGITS
    Eileen
    0.70
     Eileen
    0.63
    й
    0.61
     useRef
    0.60
     eil
    0.58
     PGP
    0.56
    ist
    0.56
    CEP
    0.55
    ��������
    0.54
     Argos
    0.52
    Activations Density 0.014%

    No Known Activations