© 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. 5-CLT-HP
    7. 2221
    Prev
    Next
    INDEX
    Explanations

    to

    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
     "..\..\
    -0.85
     "..\..\..\
    -0.77
    /**
    -0.71
     MainAxisSize
    -0.65
    ">//
    -0.63
    __((
    -0.62
    brainly
    -0.62
    
    -0.60
     ModelExpression
    -0.60
     lenker
    -0.58
    POSITIVE LOGITS
     paradigm
    0.56
     soul
    0.49
     upgrades
    0.49
     attitude
    0.47
     Paradigm
    0.47
    älv
    0.47
     bitch
    0.46
     self
    0.46
     damage
    0.45
     upgrading
    0.44
    Activations Density 0.006%

    No Known Activations