© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38824
    Prev
    Next
    INDEX
    Explanations

    States

    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
     States
    -1.17
     states
    -1.16
    States
    -1.14
     STATES
    -1.11
    states
    -1.01
     états
    -0.83
     estados
    -0.82
    STATES
    -0.75
     Etats
    -0.67
     Estados
    -0.61
    POSITIVE LOGITS
     myſelf
    1.26
     Efq
    1.23
     itſelf
    1.20
     Majefty
    1.06
    rungsseite
    1.05
    LookAnd
    1.05
     يتيمه
    1.05
     Shakspeare
    1.05
     themſelves
    1.00
     tfsi
    1.00
    Activations Density 0.590%

    No Known Activations