© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1398
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and reactions, especially those involving copper, nitrogen, and ammonium compounds

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    UnsafeEnabled
    -0.88
     estekak
    -0.76
     protoimpl
    -0.67
    awtextra
    -0.64
    QMetaType
    -0.60
    WriteBarrier
    -0.60
    RemoveField
    -0.60
    sizeCache
    -0.59
    StoryboardSegue
    -0.58
     Dernière
    -0.56
    POSITIVE LOGITS
    Cl
    0.73
     Cl
    0.69
    CO
    0.63
    NO
    0.58
     CO
    0.57
    SO
    0.56
    OH
    0.54
     OH
    0.54
     NH
    0.54
    #+#
    0.54
    Activations Density 0.444%

    No Known Activations