© 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. 4-CLT-HP
    7. 3539
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    CJK
    -0.57
    PRC
    -0.50
    LEC
    -0.47
    EME
    -0.46
    ETYPE
    -0.44
    formKey
    -0.43
    LARE
    -0.43
     conf
    -0.43
    CCO
    -0.43
    EDE
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.72
     AssemblyCulture
    0.68
     mourut
    0.65
     nakalista
    0.64
     للمعارف
    0.63
     esternos
    0.63
    onAttach
    0.62
     gynhyrchwyd
    0.62
     vôtre
    0.62
    tonsoft
    0.59
    Activations Density 0.003%

    No Known Activations