© 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. 44161
    Prev
    Next
    INDEX
    Explanations

    Web or TV

    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
     
    -0.63
    ↵
    -0.59
    -
    -0.54
      
    -0.48
    ↵↵
    -0.45
    ↵↵↵
    -0.43
    ,
    -0.43
     "
    -0.42
     I
    -0.42
     TV
    -0.42
    POSITIVE LOGITS
     صوتيه
    1.19
    tagHelperRunner
    1.13
     Monfieur
    1.10
     AssemblyCulture
    1.09
     Houſe
    1.08
     Conſ
    1.07
     surla
    1.07
     houſe
    1.06
    )++;
    1.05
     myſelf
    1.05
    Activations Density 0.300%

    No Known Activations