© 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. 21846
    Prev
    Next
    INDEX
    Explanations

    biological terms and phrases related to cellular processes and molecular structures

    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
    دانشنامهٔ
    -1.16
     виправивши
    -1.15
    fjspx
    -1.08
     Мексичка
    -1.06
    Personensuche
    -1.06
     متعلقه
    -1.03
    bewerken
    -1.00
    ThroughAttribute
    -1.00
    SourceChecksum
    -1.00
    adpleegd
    -0.99
    POSITIVE LOGITS
     part
    0.59
     as
    0.47
     even
    0.46
     this
    0.45
     all
    0.43
     just
    0.43
     in
    0.42
     off
    0.42
     also
    0.40
     within
    0.40
    Activations Density 0.163%

    No Known Activations