© 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. 0-CLT-HP
    7. 38875
    Prev
    Next
    INDEX
    Explanations

    idity

    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
     صوتيه
    -0.95
    DockStyle
    -0.87
    BeforeClass
    -0.72
    idity
    -0.71
    icitis
    -0.71
     EClass
    -0.71
    orsese
    -0.70
     Agenda
    -0.70
    ophores
    -0.69
    Erstellt
    -0.69
    POSITIVE LOGITS
     гото
    0.40
     seul
    0.39
    合
    0.39
     занимается
    0.38
    大
    0.37
     cherchés
    0.36
     bro
    0.36
    стъ
    0.36
    o
    0.35
     inti
    0.35
    Activations Density 0.036%

    No Known Activations