© 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. 74539
    Prev
    Next
    INDEX
    Explanations

    sea

    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
    feer
    -0.56
    Decoded
    -0.50
    Contin
    -0.49
    بيرة
    -0.48
    Bet
    -0.48
    andidates
    -0.47
     Shed
    -0.47
    vora
    -0.46
    paddingVertical
    -0.46
    atera
    -0.46
    POSITIVE LOGITS
     initComponents
    0.64
     esternos
    0.64
     Roskov
    0.58
     &___
    0.56
    bootstrapcdn
    0.56
    wall
    0.54
     resourceCulture
    0.53
    EndInit
    0.51
     pank
    0.51
     kasarigan
    0.50
    Activations Density 0.000%

    No Known Activations