© 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. 24
    Prev
    Next
    INDEX
    Explanations

    words or phrases common in research or scientific academic papers

    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
    Personensuche
    -0.75
    elemField
    -0.73
    principalColumn
    -0.69
    Knows
    -0.67
    toHaveBeenCalled
    -0.63
    ResumeLayout
    -0.62
    windowFixed
    -0.60
     Wants
    -0.59
    knows
    -0.59
    HasIndex
    -0.57
    POSITIVE LOGITS
     are
    2.88
     were
    1.92
     have
    1.88
     can
    1.51
     aren
    1.49
     may
    1.41
     seem
    1.37
     appear
    1.37
     will
    1.35
    are
    1.34
    Activations Density 5.375%

    No Known Activations