© 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. 1152
    Prev
    Next
    INDEX
    Explanations

    Website snippets

    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
    More
    -0.69
     More
    -0.65
     Most
    -0.63
    Most
    -0.63
    ChildScrollView
    -0.59
    PasswordEncoder
    -0.57
    ParallelGroup
    -0.52
    IZABETH
    -0.51
     Many
    -0.49
    Many
    -0.48
    POSITIVE LOGITS
    MergeFrom
    0.71
     >=",
    0.67
     pinulongan
    0.64
     Bellow
    0.56
     Coming
    0.52
    anzia
    0.52
    ResumeLayout
    0.50
    存于互联网档案馆
    0.50
     برانيه
    0.49
     Requests
    0.49
    Activations Density 0.021%

    No Known Activations