© 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. 5-CLT-HP
    7. 1110
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     esternos
    -0.68
    цездатний
    -0.68
     betweenstory
    -0.64
    migrationBuilder
    -0.61
     <=",
    -0.61
     Italijani
    -0.60
    addTab
    -0.59
    ⓧ
    -0.59
     gynhyrchwyd
    -0.58
     AssemblyCompany
    -0.57
    POSITIVE LOGITS
    pro
    0.52
    ng
    0.47
    Pro
    0.45
    RefNanny
    0.45
    ]};
    0.44
    ]]:
    0.43
    ']):
    0.43
    GeneratedValue
    0.42
     soins
    0.42
    tende
    0.42
    Activations Density 0.072%

    No Known Activations