© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    sequential process

    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
    为止
    -0.77
     ostavi
    -0.68
    rungsseite
    -0.60
    +#+#
    -0.59
    itaal
    -0.56
    batore
    -0.56
     Normdatei
    -0.55
    Personendaten
    -0.54
     poi
    -0.54
    complexContent
    -0.53
    POSITIVE LOGITS
     ProtoMessage
    0.47
    しつつ
    0.45
    WarningLevel
    0.45
     btw
    0.45
     Gaul
    0.44
    StoryboardSegue
    0.43
    ędzie
    0.42
     frattempo
    0.42
     OMITBAD
    0.41
     mme
    0.41
    Activations Density 0.053%

    No Known Activations