© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44160
    Prev
    Next
    INDEX
    Explanations

    says

    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
     EconPapers
    -0.67
    انيف
    -0.66
    enumi
    -0.62
    ikian
    -0.62
    ///</
    -0.57
     ComVisible
    -0.57
     JUGA
    -0.56
    дравству
    -0.55
     hoạch
    -0.54
    OGND
    -0.53
    POSITIVE LOGITS
    .
    0.52
    stateProvider
    0.51
     Bridges
    0.47
     Mounting
    0.45
    Odkazy
    0.45
     sinistro
    0.45
    ignac
    0.44
    Referencie
    0.44
     Replacing
    0.43
     Estimation
    0.43
    Activations Density 0.019%

    No Known Activations