© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2758
    Prev
    Next
    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Part
    -0.54
    ly
    -0.50
    ernoo
    -0.48
    zusch
    -0.48
    Part
    -0.48
    ness
    -0.47
    ())));
    -0.46
     ""),
    -0.46
     parts
    -0.45
    outline
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.73
     Wiktionnaire
    0.69
    hirt
    0.57
    ProgressHUD
    0.57
    ByPrimaryKey
    0.57
    OnInit
    0.56
     snout
    0.56
     Akismet
    0.56
    adget
    0.55
     doubtnut
    0.55
    Activations Density 0.000%

    No Known Activations