© 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. 1076
    Prev
    Next
    INDEX
    Explanations

    transistor

    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
     GenerationType
    -0.91
    ChildScrollView
    -0.90
     onAnimation
    -0.85
     BorderRadius
    -0.82
    SequentialGroup
    -0.81
     TextInputType
    -0.81
    WebVitals
    -0.76
    InputBorder
    -0.75
    RectangleBorder
    -0.75
    ReusableCell
    -0.75
    POSITIVE LOGITS
    .
    0.69
     in
    0.63
    ))),
    0.60
     for
    0.60
     with
    0.57
     that
    0.57
     and
    0.57
    }}}
    0.56
    ↵↵
    0.55
     within
    0.55
    Activations Density 0.290%

    No Known Activations