© 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. 2052
    Prev
    Next
    INDEX
    Explanations

    Non-English languages

    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
    EDEFAULT
    -0.65
     eventdata
    -0.65
    <bos>
    -0.65
    Personendaten
    -0.63
    Vidite
    -0.63
    Portail
    -0.55
    DebuggerNonUser
    -0.54
     transférez
    -0.53
    UnusedPrivate
    -0.53
    EndContext
    -0.52
    POSITIVE LOGITS
     tangential
    0.57
    osoever
    0.51
    ództ
    0.49
    //});
    0.48
     })}
    0.48
    Referencie
    0.48
     eléctricos
    0.48
    .
    0.47
    atherine
    0.47
     husbands
    0.47
    Activations Density 0.001%

    No Known Activations