© 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. 3336
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to electrostatics and molecular systems

    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
    äischen
    -0.69
     صوتيه
    -0.56
    indest
    -0.54
    ichel
    -0.54
    ductory
    -0.54
    =-=-=-=-
    -0.52
     محفوظة
    -0.50
    sterious
    -0.49
    jší
    -0.49
    rassing
    -0.49
    POSITIVE LOGITS
    يكب
    0.79
    +#+#
    0.75
    __);
    0.70
    VersionUID
    0.66
     himo
    0.64
     gages
    0.62
     violets
    0.60
    ualitas
    0.58
    featureID
    0.58
     Wiktionnaire
    0.58
    Activations Density 1.185%

    No Known Activations