© 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. 18-RES-MATRYOSHKA-DC
    7. 330
    Prev
    Next
    INDEX
    Explanations

    intensifiers, especially "greatly" and words/phrases that go with it to add emphasis.

    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.18.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.18.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
    ReusableCell
    -0.74
    /***/
    -0.63
     somehow
    -0.57
    missione
    -0.54
     consec
    -0.53
     Schal
    -0.52
    全く
    -0.52
    jds
    -0.51
     endless
    -0.50
     Todes
    -0.50
    POSITIVE LOGITS
    SourceChecksum
    0.82
    enough
    0.81
     amounts
    0.77
    amounts
    0.77
    FieldBuilder
    0.76
     מאוד
    0.72
     enough
    0.71
     sekali
    0.70
     (>
    0.69
     Amounts
    0.66
    Activations Density 1.543%

    No Known Activations