© 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. 20-CLT-HP
    7. 74706
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act-logits · 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
    Personendaten
    -0.91
    bootstrapcdn
    -0.79
    NewUrlParser
    -0.73
    WebControls
    -0.73
     EconPapers
    -0.71
    帖最后由
    -0.67
    ClientSize
    -0.65
     IBOutlet
    -0.64
    Datuak
    -0.63
     CURIAM
    -0.60
    POSITIVE LOGITS
    fromnode
    0.58
     mono
    0.51
     dio
    0.47
     gym
    0.47
     jard
    0.45
     drum
    0.44
    keit
    0.43
     Gerr
    0.43
    uric
    0.42
    ]<<"
    0.42
    Activations Density 0.001%

    No Known Activations