© 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. 0-CLT-HP
    4. 43618
    Prev
    Next
    INDEX
    Explanations

    albumin

    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
    Ours
    -0.52
     كومونز
    -0.48
    Sucesor
    -0.46
     >=",
    -0.45
     nawr
    -0.43
    derive
    -0.42
    astia
    -0.41
    Filmografia
    -0.41
     מוע
    -0.41
    SourceChecksum
    -0.41
    POSITIVE LOGITS
    انجليز
    0.64
    NgModule
    0.63
    ToProps
    0.62
    instancetype
    0.62
     buurt
    0.61
     ListNode
    0.60
    Portail
    0.59
    vacy
    0.58
     Loch
    0.58
    swire
    0.57
    Activations Density 0.151%

    No Known Activations