© 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. 18-RES-MATRYOSHKA-DC
    7. 977
    Prev
    Next
    INDEX
    Explanations

    the word "out" and words often appearing nearby, such as "of", "patient", and "grow"

    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.18.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.18.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
     صوتيه
    -0.90
    complexContent
    -0.79
    Javadoc
    -0.69
     <<<<<<<<<<<<<<
    -0.68
     فريبيس
    -0.67
    SequentialGroup
    -0.66
    ValueStyle
    -0.66
    styleable
    -0.64
    lieferung
    -0.64
    initComponents
    -0.64
    POSITIVE LOGITS
     OUT
    1.10
     Out
    1.02
     out
    1.00
    Out
    0.90
    out
    0.87
    OUT
    0.82
    getOut
    0.68
     loud
    0.66
     fuori
    0.65
    pout
    0.63
    Activations Density 1.028%

    No Known Activations