© 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. 0-RES-MATRYOSHKA-DC
    4. 11022
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds, notably acetamide and related bioactive molecules

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.66
    Bless
    -0.65
     rhestr
    -0.64
    __':
    
    -0.64
    ressive
    -0.64
    ressed
    -0.61
    ReusableCell
    -0.60
    mapStateToProps
    -0.59
    calaure
    -0.59
    LLocation
    -0.58
    POSITIVE LOGITS
    ace
    2.75
    acea
    0.88
    aceae
    0.87
    aces
    0.67
    ACE
    0.54
    nace
    0.53
     frattempo
    0.52
    pace
    0.51
    air
    0.49
    áce
    0.48
    Activations Density 0.000%

    No Known Activations