© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1216
    Prev
    Next
    INDEX
    Explanations

    qualifiers indicating subtle degrees or variations in characteristics

    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
     richesse
    -0.55
     ríos
    -0.53
    makeConstraints
    -0.50
     laad
    -0.50
     Inscrivez
    -0.48
    誰が
    -0.48
     puissante
    -0.48
     principal
    -0.47
    Vezi
    -0.47
    !”
    -0.47
    POSITIVE LOGITS
     المعيارى
    1.08
    Slight
    1.07
     Etwas
    1.07
    Somewhat
    1.03
     bisschen
    1.02
    slightly
    1.02
     slightly
    1.02
     trochę
    1.02
     bit
    1.01
     کمی
    1.01
    Activations Density 0.739%

    No Known Activations