© 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. 1-RES-MATRYOSHKA-DC
    7. 534
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "forming" or "formation" in various contexts

    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
     متعلقه
    -0.79
    rungsseite
    -0.77
     objectAtIndex
    -0.76
    adaptiveStyles
    -0.73
    InSection
    -0.71
     ویکی‌پدیا
    -0.69
    happen
    -0.69
    locene
    -0.68
    JNIEnv
    -0.67
    IntoConstraints
    -0.66
    POSITIVE LOGITS
     form
    4.69
     Form
    4.13
    form
    4.03
    Form
    3.95
     FORM
    3.73
     forms
    3.61
     Forms
    3.38
    FORM
    3.22
    forms
    3.09
     FORMS
    3.03
    Activations Density 0.776%

    No Known Activations