© 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. 92129
    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
    SequentialGroup
    -0.78
    HomeAsUpEnabled
    -0.72
    ragalactic
    -0.68
    PerformLayout
    -0.68
     kanssa
    -0.67
     betweenstory
    -0.67
    nastics
    -0.67
    OGND
    -0.66
    antaranya
    -0.66
     vermelhas
    -0.66
    POSITIVE LOGITS
     the
    1.30
     a
    1.01
     its
    0.87
     an
    0.83
     no
    0.82
     regard
    0.81
    stood
    0.76
     respect
    0.74
     regards
    0.71
     their
    0.70
    Activations Density 0.030%

    No Known Activations