© 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. 11338
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and inequalities

    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
    providedIn
    -0.68
    UpdateCommand
    -0.64
    AndroidJUnit
    -0.59
     Италијани
    -0.59
     MotionEvent
    -0.55
    PerformLayout
    -0.54
     <=",
    -0.52
     censiti
    -0.52
     صوتيه
    -0.51
    mainAxisSize
    -0.50
    POSITIVE LOGITS
    <!--[
    0.69
    NUMX
    0.65
    umenical
    0.64
    SdkVersion
    0.63
    <_>
    0.63
    annu
    0.62
    FieldNumber
    0.61
    saraba
    0.59
     מלא
    0.58
    PLICATIONS
    0.56
    Activations Density 0.011%

    No Known Activations