© 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. 1599
    Prev
    Next
    INDEX
    Explanations

    "come to" or "come up" phrases, with additional activation for instances of "centuries to" "several to"

    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
    WebControls
    -0.72
    kloped
    -0.69
    istic
    -0.59
    nonatomic
    -0.58
    ulaire
    -0.57
    הערות
    -0.57
    abetes
    -0.57
    RetentionPolicy
    -0.56
    SpringRunner
    -0.56
    GroupLayout
    -0.54
    POSITIVE LOGITS
    Came
    0.84
    Comes
    0.77
    came
    0.73
     COME
    0.68
     Came
    0.68
    SequentialGroup
    0.66
     CAME
    0.65
     Comes
    0.64
     COMES
    0.63
     comes
    0.60
    Activations Density 0.132%

    No Known Activations