© 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. 16135
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations involving 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
    VersionUID
    -0.99
    tvguidetime
    -0.89
     disambiguazione
    -0.89
    WriteLiteral
    -0.82
     nakalista
    -0.81
     transférez
    -0.79
    ervlak
    -0.78
     Relo
    -0.77
    Vidu
    -0.76
    حياته
    -0.73
    POSITIVE LOGITS
     long
    0.45
     BrowserRouter
    0.44
     I
    0.43
     O
    0.41
     in
    0.40
    XMLSchema
    0.40
     each
    0.40
     T
    0.39
    ftagPool
    0.39
     a
    0.39
    Activations Density 0.084%

    No Known Activations