© 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. 45283
    Prev
    Next
    INDEX
    Explanations

    inside

    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
     inside
    -1.66
    inside
    -1.42
    Inside
    -1.34
     INSIDE
    -1.27
     Inside
    -1.25
     dedans
    -1.06
     adentro
    -1.05
    intérieur
    -1.04
     intérieure
    -1.04
    INSIDE
    -1.02
    POSITIVE LOGITS
     the
    0.84
    Personensuche
    0.82
     a
    0.75
     censiti
    0.64
    UnknownFieldSet
    0.62
    XmlAccessType
    0.61
    encodeWith
    0.60
     those
    0.60
     jScrollPane
    0.59
     their
    0.59
    Activations Density 0.026%

    No Known Activations