Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3649
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    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
    lehem
    -0.47
     pè
    -0.39
    ukone
    -0.36
     famili
    -0.35
    ActionBar
    -0.35
     seva
    -0.34
    ěř
    -0.34
    ."]
    -0.33
     famil
    -0.33
     Mame
    -0.33
    POSITIVE LOGITS
     мәкал
    1.01
    featureID
    0.96
     <=",
    0.92
    :✨
    0.91
    enterOuterAlt
    0.86
     '\\;'
    0.86
     '{@
    0.85
     AssemblyCulture
    0.84
    astify
    0.84
    原始内容存档于
    0.84
    Activations Density 0.010%

    No Known Activations