© 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. 12-RES-MATRYOSHKA-DC
    7. 26076
    Prev
    Next
    INDEX
    Explanations

    instances of high activation punctuation or specific phrases related to significant news events or statements

    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
     men
    -0.59
    agi
    -0.55
     that
    -0.54
    trate
    -0.53
     mà
    -0.48
     Vaid
    -0.48
    бина
    -0.47
    ाल
    -0.47
    abler
    -0.47
    FORMANCE
    -0.47
    POSITIVE LOGITS
     Roskov
    0.77
    tvguidetime
    0.69
    principalColumn
    0.66
    
    0.66
    存于互联网档案馆
    0.64
     tartalomajánló
    0.63
     []).
    0.60
    bestos
    0.58
    verläs
    0.58
     Мексичка
    0.58
    Activations Density 0.067%

    No Known Activations