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. 18997
    Prev
    Next
    INDEX
    Explanations

    phrases related to transitions or origins

    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
    Affirmed
    -0.58
    IntoConstraints
    -0.58
    来自
    -0.53
     Dijk
    -0.53
    來自
    -0.53
    Дереккөздер
    -0.50
    yntaxException
    -0.50
    braz
    -0.49
    niczka
    -0.49
    equila
    -0.48
    POSITIVE LOGITS
     nahilalakip
    0.55
     nakalista
    0.54
     Peyton
    0.53
    stdc
    0.53
    LLocation
    0.52
     Gleaner
    0.52
    zulegen
    0.52
     rospy
    0.52
    endphp
    0.52
    zustellen
    0.51
    Activations Density 0.015%

    No Known Activations