© 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. 22-RES-MATRYOSHKA-DC
    7. 2845
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate limits and the boundaries of those limits

    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.22.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.22.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
    RTLR
    -0.57
     referenties
    -0.56
    glLoadIdentity
    -0.54
     situazione
    -0.54
    անո
    -0.53
    abestanden
    -0.53
     <<<<<<<<<<<<<<
    -0.52
     altrett
    -0.52
    extAlignment
    -0.51
    HtmlAttribute
    -0.49
    POSITIVE LOGITS
     scope
    1.45
     bounds
    1.37
     confines
    1.32
     purview
    1.23
     limits
    1.21
     boundaries
    1.21
    scope
    1.16
    Scope
    1.10
     reach
    1.06
     borders
    1.06
    Activations Density 0.324%

    No Known Activations