© 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. 2716
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    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
     '\\;'
    -1.01
     MainAxisSize
    -0.88
    Personensuche
    -0.73
    EndContext
    -0.72
    ]")]
    -0.68
     cherchés
    -0.68
     للمعارف
    -0.68
    DOCTYPE
    -0.67
    rrggbb
    -0.66
     Infórmanos
    -0.66
    POSITIVE LOGITS
    insegna
    0.56
    appartamento
    0.48
     including
    0.47
    utnik
    0.46
     firm
    0.45
    presso
    0.44
    setTime
    0.42
    lní
    0.42
    onner
    0.42
    reek
    0.42
    Activations Density 0.699%

    No Known Activations