© 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. 1-CLT-HP
    7. 435
    Prev
    Next
    INDEX
    Explanations

    children

    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
     Arboretum
    -0.58
     Burnt
    -0.55
    enumi
    -0.54
     }_{\
    -0.54
    Демографія
    -0.51
    InputBorder
    -0.48
    OGND
    -0.48
     Nerv
    -0.48
     Catawiki
    -0.48
    UnusedPrivate
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.62
    SPATH
    0.55
     classifiers
    0.54
    GrantedAuthority
    0.54
    classifiers
    0.50
    onAttach
    0.49
    mox
    0.49
     nozzles
    0.48
     formations
    0.48
     centavos
    0.48
    Activations Density 0.018%

    No Known Activations