© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11417
    Prev
    Next
    INDEX
    Explanations

    words indicating conclusions or logical inferences

    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
    AddTagHelper
    -0.84
     AssemblyCulture
    -0.81
    ValueStyle
    -0.81
    loài
    -0.74
    новништво
    -0.71
    glEnd
    -0.71
    endphp
    -0.69
     pinulongan
    -0.69
    extAlignment
    -0.68
    SBATCH
    -0.67
    POSITIVE LOGITS
    الدراسه
    0.58
     aange
    0.50
     Met
    0.43
     Madsen
    0.42
    اتي
    0.42
    arar
    0.42
    essive
    0.41
    YV
    0.41
    mittlung
    0.41
     defStyle
    0.41
    Activations Density 0.010%

    No Known Activations