Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95402
    Prev
    Next
    INDEX
    Explanations

    questions

    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
     AssemblyCulture
    -0.93
    AndEndTag
    -0.87
    ########.
    -0.76
    ThroughAttribute
    -0.69
     tartalomajánló
    -0.66
     kasarigan
    -0.64
    Personendaten
    -0.63
    SequentialGroup
    -0.63
    Enllaces
    -0.61
    AppMethodBeat
    -0.60
    POSITIVE LOGITS
     are
    0.70
     does
    0.63
     can
    0.61
     should
    0.56
     is
    0.55
     aren
    0.54
    */;
    0.54
     etc
    0.53
     will
    0.53
    — 
    0.52
    Activations Density 0.001%

    No Known Activations