© 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. 91138
    Prev
    Next
    INDEX
    Explanations

    hundred

    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
     hundred
    -0.96
     transfieras
    -0.94
    tagHelperRunner
    -0.67
    ]")]
    -0.65
    RegistryLite
    -0.63
     Wikiseite
    -0.61
     centaines
    -0.61
    ']))
    
    -0.60
    hundred
    -0.60
    andowski
    -0.60
    POSITIVE LOGITS
    ness
    0.57
    CppMethod
    0.56
    matically
    0.55
    matic
    0.53
    vation
    0.52
    Portail
    0.51
    dom
    0.50
    don
    0.50
    ly
    0.50
    mer
    0.50
    Activations Density 1.621%

    No Known Activations