© 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. 24-RES-MATRYOSHKA-DC
    7. 631
    Prev
    Next
    INDEX
    Explanations

    legalese relating to constitutional rights like freedom of speech

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     برانيه
    -0.60
    DockStyle
    -0.60
     оригіналу
    -0.53
    تقاوى
    -0.53
    OGND
    -0.52
     estimés
    -0.52
     disparu
    -0.51
     départ
    -0.49
    windowFixed
    -0.49
    WithFormat
    -0.48
    POSITIVE LOGITS
     speech
    1.01
    speech
    0.83
     Speech
    0.82
    Speech
    0.82
    peech
    0.74
     SPEECH
    0.74
     expression
    0.73
     expressive
    0.73
     publishers
    0.70
     censorship
    0.69
    Activations Density 1.312%

    No Known Activations