© 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. 0-CLT-HP
    7. 45234
    Prev
    Next
    INDEX
    Explanations

    phosphate

    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
    tershire
    -1.25
    encils
    -1.16
    hematical
    -1.13
    iffance
    -1.10
    ipheral
    -1.09
    duled
    -1.09
    æus
    -1.07
    ſhip
    -1.05
    ratulations
    -1.03
    vrolet
    -1.02
    POSITIVE LOGITS
     Oedipus
    0.75
     Manly
    0.75
    ValueStyle
    0.74
     manna
    0.74
     Pilate
    0.72
     Achilles
    0.71
    win
    0.69
     AssemblyCulture
    0.69
     Crusoe
    0.69
     Chicano
    0.69
    Activations Density 0.063%

    No Known Activations