© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 2770
    Prev
    Next
    INDEX
    Explanations

    elements related to calculations, particularly mathematical operations and factors

    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
    forge
    -0.49
     that
    -0.46
    utter
    -0.46
    link
    -0.46
    Cpp
    -0.45
    ტერ
    -0.44
    -
    -0.44
    vita
    -0.41
     f
    -0.41
    form
    -0.40
    POSITIVE LOGITS
    MLLoader
    1.05
     صوتيه
    0.92
    +:+
    0.73
    utilisons
    0.66
     Administrativna
    0.66
     gynhyrchwyd
    0.66
     Signalez
    0.66
    DoubleQuotes
    0.65
    CodedInputStream
    0.65
    ztus
    0.63
    Activations Density 0.071%

    No Known Activations