Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 21401
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and the end of statements

    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
     ‘
    -0.45
    ardı
    -0.44
     «
    -0.44
    MathML
    -0.43
     sơn
    -0.42
     Gemein
    -0.40
     parem
    -0.40
    pc
    -0.40
    ter
    -0.40
    går
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.92
    GraphicsUnit
    0.91
     EconPapers
    0.89
    ConstraintMaker
    0.87
    adaptiveStyles
    0.87
     BoxDecoration
    0.83
    SBATCH
    0.82
     typelib
    0.82
    uxxxx
    0.82
    msgTypes
    0.81
    Activations Density 0.001%

    No Known Activations