© 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. 5-CLT-HP
    4. 96075
    Prev
    Next
    INDEX
    Explanations

    credit

    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
    '],
    
    -1.10
    '),
    
    -1.09
    !',
    -1.06
     الحره
    -1.04
     >=",
    -1.02
    ."],
    -1.02
    '):
    
    -1.01
    !&
    -0.99
    )•
    -0.99
    "),
    
    -0.98
    POSITIVE LOGITS
    ImageContext
    0.41
    netbeans
    0.38
     muuta
    0.37
     russa
    0.37
     such
    0.36
    internalType
    0.36
     latine
    0.35
     russes
    0.35
     hilang
    0.35
     Decken
    0.34
    Activations Density 0.000%

    No Known Activations