© 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. 24-RES-MATRYOSHKA-DC
    7. 160
    Prev
    Next
    INDEX
    Explanations

    the word "no" and words and phrases that indicate negation or an absence of something

    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.24.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.24.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
     متعلقه
    -0.73
     Roskov
    -0.72
    сього
    -0.69
    EDEFAULT
    -0.63
    Bioaccumulative
    -0.62
    Various
    -0.60
    kadang
    -0.60
     tantôt
    -0.60
     vooral
    -0.59
     Various
    -0.58
    POSITIVE LOGITS
     doubt
    1.00
     discernible
    0.91
     indication
    0.91
     appreciable
    0.89
     longer
    0.87
     further
    0.86
     mention
    0.85
     other
    0.83
     clue
    0.82
     such
    0.81
    Activations Density 1.312%

    No Known Activations