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. 0-CLT-HP
    4. 91808
    Prev
    Next
    INDEX
    Explanations

    RED

    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
    HER
    -0.83
    RED
    -0.71
    le
    -0.68
    here
    -0.56
    her
    -0.56
     RED
    -0.56
    p
    -0.55
    ma
    -0.52
    ke
    -0.51
    LE
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.86
    دانشنامهٔ
    0.84
    GraphicsUnit
    0.82
     Signalez
    0.81
     kaarangay
    0.80
     myſelf
    0.79
     ExecuteAsync
    0.79
    =$?
    0.78
    StoryboardSegue
    0.77
    ')):
    0.77
    Activations Density 0.950%

    No Known Activations