© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26191
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'h'

    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
    évaluateur
    -0.57
    IntoConstraints
    -0.55
     Vort
    -0.51
     NUE
    -0.51
    NameInMap
    -0.51
     виправивши
    -0.50
    WithIOException
    -0.50
     poète
    -0.50
     acamp
    -0.47
     Niemand
    -0.47
    POSITIVE LOGITS
    cstring
    1.18
    TypedDataSet
    0.65
    SceneManagement
    0.63
     الحره
    0.62
    VIAF
    0.62
     protoimpl
    0.60
    uties
    0.59
    BoxShadow
    0.59
    EventManager
    0.58
    skjaer
    0.57
    Activations Density 0.000%

    No Known Activations