© 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. 95070
    Prev
    Next
    INDEX
    Explanations

    yet

    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
    </caption>
    -0.73
    évaluateur
    -0.68
    
    -0.61
    exitRule
    -0.61
     utafitiHapana
    -0.60
     Wikimedijinoj
    -0.58
    ']));
    -0.58
     Réponses
    -0.57
     ProtoMessage
    -0.56
    ])):
    -0.55
    POSITIVE LOGITS
    ,
    0.54
     I
    0.54
     we
    0.53
    spricht
    0.50
     compare
    0.50
    preventDefault
    0.49
     banning
    0.49
    Alongside
    0.48
    ächlich
    0.48
    куда
    0.48
    Activations Density 0.001%

    No Known Activations