© 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. 4-CLT-HP
    7. 4370
    Prev
    Next
    INDEX
    Explanations

    with

    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
    migrationBuilder
    -0.66
    AutoScaleMode
    -0.63
     صوتيه
    -0.60
    nonatomic
    -0.59
    PerformLayout
    -0.56
    
    -0.54
    +#+#
    -0.53
    AxisAlignment
    -0.52
    RunWith
    -0.50
    __((
    -0.50
    POSITIVE LOGITS
    kloped
    0.54
     people
    0.54
     estekak
    0.52
     byste
    0.52
     Normdatei
    0.52
    Datuak
    0.51
     getRule
    0.48
     about
    0.47
    XDECREF
    0.47
     Indones
    0.46
    Activations Density 0.002%

    No Known Activations