© 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. 1101
    Prev
    Next
    INDEX
    Explanations

    how to select text using the keyboard

    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
    脚注の使い方
    -0.56
    ernalia
    -0.54
    HtmlAttribute
    -0.50
     vernis
    -0.48
    TemporalType
    -0.47
     Phipps
    -0.47
    UnsafeEnabled
    -0.47
     tannins
    -0.47
    ровано
    -0.47
     automatiques
    -0.47
    POSITIVE LOGITS
     keys
    1.18
     key
    1.14
     keyboard
    1.02
     Key
    0.98
     Keys
    0.98
     pressing
    0.96
    Key
    0.93
    Keys
    0.92
    key
    0.92
    keys
    0.91
    Activations Density 0.854%

    No Known Activations