Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 29497
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and conjectures about hypothetical situations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    ſelf
    -0.82
    RefNanny
    -0.72
     ſhould
    -0.71
    tvguidetime
    -0.71
    ſelves
    -0.71
    AndEndTag
    -0.71
    -------------</
    -0.69
    IndentedString
    -0.69
     Majefty
    -0.69
     Efq
    -0.68
    POSITIVE LOGITS
    пресс
    0.53
    我就
    0.52
    ilstein
    0.51
    peritoneal
    0.48
     قرار
    0.47
     ciri
    0.46
     következő
    0.45
     F
    0.45
    AppCompat
    0.45
     
    0.45
    Activations Density 0.024%

    No Known Activations