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. 22634
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "it."

    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
     fullt
    -0.50
     وك
    -0.49
     Normdatei
    -0.48
     activos
    -0.47
     We
    -0.47
     I
    -0.47
     hvor
    -0.47
     langt
    -0.47
     pregi
    -0.47
    ri
    -0.46
    POSITIVE LOGITS
     Theſe
    1.23
     themſelves
    1.00
     Majefty
    0.99
     Efq
    0.99
     Monfieur
    0.98
     himſelf
    0.96
     purpoſe
    0.95
     reaſon
    0.94
     Beſ
    0.91
     Anſ
    0.91
    Activations Density 0.067%

    No Known Activations