© 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. 1979
    Prev
    Next
    INDEX
    Explanations

    complete sentences

    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
    principalTable
    -0.75
    oneofs
    -0.73
    Tikang
    -0.72
    +#+#
    -0.68
     defaultstate
    -0.68
    tagHelperRunner
    -0.66
    preferably
    -0.66
    PhysRev
    -0.65
     EdgeInsets
    -0.65
     getItemId
    -0.65
    POSITIVE LOGITS
    šinou
    0.38
    ૈ
    0.38
    bbene
    0.38
     amelyek
    0.38
    ressible
    0.38
     Suff
    0.36
     cães
    0.36
    ingroup
    0.34
     disebabkan
    0.34
    Gön
    0.34
    Activations Density 0.000%

    No Known Activations