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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 330
    Prev
    Next
    INDEX
    Explanations

    objectives and goals

    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
    TagMode
    -0.59
    جغرافيا
    -0.58
    ConstraintMaker
    -0.55
     comuniques
    -0.54
    ёх
    -0.53
    SequentialGroup
    -0.53
     surla
    -0.52
    TagHelper
    -0.52
    indest
    -0.52
    ovan
    -0.52
    POSITIVE LOGITS
     propOrder
    0.59
     mergeFrom
    0.57
     lake
    0.52
     lakes
    0.51
    üße
    0.50
     Roskov
    0.50
    lakes
    0.48
    boats
    0.47
    writeField
    0.47
    lake
    0.47
    Activations Density 0.017%

    No Known Activations