© 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. 45265
    Prev
    Next
    INDEX
    Explanations

    load

    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
    Personendaten
    -0.74
     BoxFit
    -0.67
    ConstraintMaker
    -0.62
    TagMode
    -0.59
    efully
    -0.59
    geleitet
    -0.59
    catori
    -0.58
     Normdatei
    -0.56
    zzleHttp
    -0.56
    Aholisi
    -0.56
    POSITIVE LOGITS
    featureID
    0.50
     Shaksp
    0.50
     Phry
    0.47
     hors
    0.45
     masses
    0.44
     sterilization
    0.44
     ster
    0.43
     monoch
    0.43
    Спољашње
    0.42
     worshipped
    0.42
    Activations Density 0.035%

    No Known Activations