© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90648
    Prev
    Next
    INDEX
    Explanations

    duration or acting length

    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
    ſelf
    -0.74
     poffible
    -0.73
     neceſſ
    -0.71
    ChildScrollView
    -0.70
     neceffary
    -0.70
     neceff
    -0.66
     armis
    -0.66
     perfons
    -0.66
    IntoConstraints
    -0.66
     poffe
    -0.66
    POSITIVE LOGITS
    Parcelize
    0.46
    BufferException
    0.45
    vores
    0.44
    FilterChain
    0.43
    Bukkit
    0.42
     y
    0.41
    bukkit
    0.41
    [:,:,
    0.41
    argas
    0.40
    LocalizedString
    0.40
    Activations Density 0.110%

    No Known Activations