© 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. 2454
    Prev
    Next
    INDEX
    Explanations

    the word "cut" and hyphenated words beginning with "cut"

    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
    ValueStyle
    -0.81
     AssemblyVersion
    -0.77
    DataAnnotations
    -0.77
     doInBackground
    -0.73
     Toul
    -0.71
     FormGroup
    -0.69
    AutoScaleMode
    -0.68
    complexContent
    -0.68
    principalTable
    -0.66
     myſelf
    -0.65
    POSITIVE LOGITS
     cutting
    1.16
     Cut
    1.15
     cuts
    1.13
     cut
    1.13
    Cut
    1.10
    cut
    1.09
     CUT
    1.09
    cuts
    1.08
     Cutting
    1.07
    CUT
    1.07
    Activations Density 0.073%

    No Known Activations